diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-23 18:45:06 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-01-23 18:45:06 -0800 |
commit | 048ccca8c1c8f583deec3367d7df521bb1f542ae (patch) | |
tree | efa882c88f658f711d63581a3063203c63682338 /net | |
parent | b3e27d5d4a29bcc8e057b496d5ef5194addaaac0 (diff) | |
parent | 34356f64ac0df2326fa50e2d4bca6f7c03ed16c1 (diff) | |
download | linux-048ccca8c1c8f583deec3367d7df521bb1f542ae.tar.gz linux-048ccca8c1c8f583deec3367d7df521bb1f542ae.tar.bz2 linux-048ccca8c1c8f583deec3367d7df521bb1f542ae.zip |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull rdma updates from Doug Ledford:
"Initial roundup of 4.5 merge window patches
- Remove usage of ib_query_device and instead store attributes in
ib_device struct
- Move iopoll out of block and into lib, rename to irqpoll, and use
in several places in the rdma stack as our new completion queue
polling library mechanism. Update the other block drivers that
already used iopoll to use the new mechanism too.
- Replace the per-entry GID table locks with a single GID table lock
- IPoIB multicast cleanup
- Cleanups to the IB MR facility
- Add support for 64bit extended IB counters
- Fix for netlink oops while parsing RDMA nl messages
- RoCEv2 support for the core IB code
- mlx4 RoCEv2 support
- mlx5 RoCEv2 support
- Cross Channel support for mlx5
- Timestamp support for mlx5
- Atomic support for mlx5
- Raw QP support for mlx5
- MAINTAINERS update for mlx4/mlx5
- Misc ocrdma, qib, nes, usNIC, cxgb3, cxgb4, mlx4, mlx5 updates
- Add support for remote invalidate to the iSER driver (pushed
through the RDMA tree due to dependencies, acknowledged by nab)
- Update to NFSoRDMA (pushed through the RDMA tree due to
dependencies, acknowledged by Bruce)"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (169 commits)
IB/mlx5: Unify CQ create flags check
IB/mlx5: Expose Raw Packet QP to user space consumers
{IB, net}/mlx5: Move the modify QP operation table to mlx5_ib
IB/mlx5: Support setting Ethernet priority for Raw Packet QPs
IB/mlx5: Add Raw Packet QP query functionality
IB/mlx5: Add create and destroy functionality for Raw Packet QP
IB/mlx5: Refactor mlx5_ib_qp to accommodate other QP types
IB/mlx5: Allocate a Transport Domain for each ucontext
net/mlx5_core: Warn on unsupported events of QP/RQ/SQ
net/mlx5_core: Add RQ and SQ event handling
net/mlx5_core: Export transport objects
IB/mlx5: Expose CQE version to user-space
IB/mlx5: Add CQE version 1 support to user QPs and SRQs
IB/mlx5: Fix data validation in mlx5_ib_alloc_ucontext
IB/sa: Fix netlink local service GFP crash
IB/srpt: Remove redundant wc array
IB/qib: Improve ipoib UD performance
IB/mlx4: Advertise RoCE v2 support
IB/mlx4: Create and use another QP1 for RoCEv2
IB/mlx4: Enable send of RoCE QP1 packets with IP/UDP headers
...
Diffstat (limited to 'net')
-rw-r--r-- | net/rds/ib.c | 34 | ||||
-rw-r--r-- | net/rds/iw.c | 23 | ||||
-rw-r--r-- | net/sunrpc/xprt.c | 1 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/Makefile | 2 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/frwr_ops.c | 7 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma.c | 41 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 371 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 56 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_sendto.c | 33 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/svc_rdma_transport.c | 360 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/transport.c | 30 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/verbs.c | 24 | ||||
-rw-r--r-- | net/sunrpc/xprtrdma/xprt_rdma.h | 21 |
13 files changed, 744 insertions, 259 deletions
diff --git a/net/rds/ib.c b/net/rds/ib.c index f222885ac0c7..9481d55ff6cb 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -122,44 +122,34 @@ void rds_ib_dev_put(struct rds_ib_device *rds_ibdev) static void rds_ib_add_one(struct ib_device *device) { struct rds_ib_device *rds_ibdev; - struct ib_device_attr *dev_attr; /* Only handle IB (no iWARP) devices */ if (device->node_type != RDMA_NODE_IB_CA) return; - dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL); - if (!dev_attr) - return; - - if (ib_query_device(device, dev_attr)) { - rdsdebug("Query device failed for %s\n", device->name); - goto free_attr; - } - rds_ibdev = kzalloc_node(sizeof(struct rds_ib_device), GFP_KERNEL, ibdev_to_node(device)); if (!rds_ibdev) - goto free_attr; + return; spin_lock_init(&rds_ibdev->spinlock); atomic_set(&rds_ibdev->refcount, 1); INIT_WORK(&rds_ibdev->free_work, rds_ib_dev_free); - rds_ibdev->max_wrs = dev_attr->max_qp_wr; - rds_ibdev->max_sge = min(dev_attr->max_sge, RDS_IB_MAX_SGE); + rds_ibdev->max_wrs = device->attrs.max_qp_wr; + rds_ibdev->max_sge = min(device->attrs.max_sge, RDS_IB_MAX_SGE); - rds_ibdev->fmr_max_remaps = dev_attr->max_map_per_fmr?: 32; - rds_ibdev->max_1m_fmrs = dev_attr->max_mr ? - min_t(unsigned int, (dev_attr->max_mr / 2), + rds_ibdev->fmr_max_remaps = device->attrs.max_map_per_fmr?: 32; + rds_ibdev->max_1m_fmrs = device->attrs.max_mr ? + min_t(unsigned int, (device->attrs.max_mr / 2), rds_ib_fmr_1m_pool_size) : rds_ib_fmr_1m_pool_size; - rds_ibdev->max_8k_fmrs = dev_attr->max_mr ? - min_t(unsigned int, ((dev_attr->max_mr / 2) * RDS_MR_8K_SCALE), + rds_ibdev->max_8k_fmrs = device->attrs.max_mr ? + min_t(unsigned int, ((device->attrs.max_mr / 2) * RDS_MR_8K_SCALE), rds_ib_fmr_8k_pool_size) : rds_ib_fmr_8k_pool_size; - rds_ibdev->max_initiator_depth = dev_attr->max_qp_init_rd_atom; - rds_ibdev->max_responder_resources = dev_attr->max_qp_rd_atom; + rds_ibdev->max_initiator_depth = device->attrs.max_qp_init_rd_atom; + rds_ibdev->max_responder_resources = device->attrs.max_qp_rd_atom; rds_ibdev->dev = device; rds_ibdev->pd = ib_alloc_pd(device); @@ -183,7 +173,7 @@ static void rds_ib_add_one(struct ib_device *device) } rdsdebug("RDS/IB: max_mr = %d, max_wrs = %d, max_sge = %d, fmr_max_remaps = %d, max_1m_fmrs = %d, max_8k_fmrs = %d\n", - dev_attr->max_fmr, rds_ibdev->max_wrs, rds_ibdev->max_sge, + device->attrs.max_fmr, rds_ibdev->max_wrs, rds_ibdev->max_sge, rds_ibdev->fmr_max_remaps, rds_ibdev->max_1m_fmrs, rds_ibdev->max_8k_fmrs); @@ -202,8 +192,6 @@ static void rds_ib_add_one(struct ib_device *device) put_dev: rds_ib_dev_put(rds_ibdev); -free_attr: - kfree(dev_attr); } /* diff --git a/net/rds/iw.c b/net/rds/iw.c index 576f1825fc55..f4a9fff829e0 100644 --- a/net/rds/iw.c +++ b/net/rds/iw.c @@ -60,30 +60,20 @@ LIST_HEAD(iw_nodev_conns); static void rds_iw_add_one(struct ib_device *device) { struct rds_iw_device *rds_iwdev; - struct ib_device_attr *dev_attr; /* Only handle iwarp devices */ if (device->node_type != RDMA_NODE_RNIC) return; - dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL); - if (!dev_attr) - return; - - if (ib_query_device(device, dev_attr)) { - rdsdebug("Query device failed for %s\n", device->name); - goto free_attr; - } - rds_iwdev = kmalloc(sizeof *rds_iwdev, GFP_KERNEL); if (!rds_iwdev) - goto free_attr; + return; spin_lock_init(&rds_iwdev->spinlock); - rds_iwdev->dma_local_lkey = !!(dev_attr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY); - rds_iwdev->max_wrs = dev_attr->max_qp_wr; - rds_iwdev->max_sge = min(dev_attr->max_sge, RDS_IW_MAX_SGE); + rds_iwdev->dma_local_lkey = !!(device->attrs.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY); + rds_iwdev->max_wrs = device->attrs.max_qp_wr; + rds_iwdev->max_sge = min(device->attrs.max_sge, RDS_IW_MAX_SGE); rds_iwdev->dev = device; rds_iwdev->pd = ib_alloc_pd(device); @@ -111,8 +101,7 @@ static void rds_iw_add_one(struct ib_device *device) list_add_tail(&rds_iwdev->list, &rds_iw_devices); ib_set_client_data(device, &rds_iw_client, rds_iwdev); - - goto free_attr; + return; err_mr: if (rds_iwdev->mr) @@ -121,8 +110,6 @@ err_pd: ib_dealloc_pd(rds_iwdev->pd); free_dev: kfree(rds_iwdev); -free_attr: - kfree(dev_attr); } static void rds_iw_remove_one(struct ib_device *device, void *client_data) diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 2e98f4a243e5..37edea6fa92d 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -1425,3 +1425,4 @@ void xprt_put(struct rpc_xprt *xprt) if (atomic_dec_and_test(&xprt->count)) xprt_destroy(xprt); } +EXPORT_SYMBOL_GPL(xprt_put); diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile index 33f99d3004f2..dc9f3b513a05 100644 --- a/net/sunrpc/xprtrdma/Makefile +++ b/net/sunrpc/xprtrdma/Makefile @@ -2,7 +2,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o rpcrdma-y := transport.o rpc_rdma.o verbs.o \ fmr_ops.o frwr_ops.o physical_ops.o \ - svc_rdma.o svc_rdma_transport.o \ + svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \ svc_rdma_marshal.o svc_rdma_sendto.o svc_rdma_recvfrom.o \ module.o rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index c6836844bd0e..e16567389e28 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -190,12 +190,11 @@ static int frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { - struct ib_device_attr *devattr = &ia->ri_devattr; int depth, delta; ia->ri_max_frmr_depth = min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, - devattr->max_fast_reg_page_list_len); + ia->ri_device->attrs.max_fast_reg_page_list_len); dprintk("RPC: %s: device's max FR page list len = %u\n", __func__, ia->ri_max_frmr_depth); @@ -222,8 +221,8 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, } ep->rep_attr.cap.max_send_wr *= depth; - if (ep->rep_attr.cap.max_send_wr > devattr->max_qp_wr) { - cdata->max_requests = devattr->max_qp_wr / depth; + if (ep->rep_attr.cap.max_send_wr > ia->ri_device->attrs.max_qp_wr) { + cdata->max_requests = ia->ri_device->attrs.max_qp_wr / depth; if (!cdata->max_requests) return -EINVAL; ep->rep_attr.cap.max_send_wr = cdata->max_requests * diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c index 1b7051bdbdc8..c846ca9f1eba 100644 --- a/net/sunrpc/xprtrdma/svc_rdma.c +++ b/net/sunrpc/xprtrdma/svc_rdma.c @@ -55,6 +55,7 @@ unsigned int svcrdma_ord = RPCRDMA_ORD; static unsigned int min_ord = 1; static unsigned int max_ord = 4096; unsigned int svcrdma_max_requests = RPCRDMA_MAX_REQUESTS; +unsigned int svcrdma_max_bc_requests = RPCRDMA_MAX_BC_REQUESTS; static unsigned int min_max_requests = 4; static unsigned int max_max_requests = 16384; unsigned int svcrdma_max_req_size = RPCRDMA_MAX_REQ_SIZE; @@ -71,10 +72,6 @@ atomic_t rdma_stat_rq_prod; atomic_t rdma_stat_sq_poll; atomic_t rdma_stat_sq_prod; -/* Temporary NFS request map and context caches */ -struct kmem_cache *svc_rdma_map_cachep; -struct kmem_cache *svc_rdma_ctxt_cachep; - struct workqueue_struct *svc_rdma_wq; /* @@ -243,17 +240,16 @@ void svc_rdma_cleanup(void) svc_unreg_xprt_class(&svc_rdma_bc_class); #endif svc_unreg_xprt_class(&svc_rdma_class); - kmem_cache_destroy(svc_rdma_map_cachep); - kmem_cache_destroy(svc_rdma_ctxt_cachep); } int svc_rdma_init(void) { dprintk("SVCRDMA Module Init, register RPC RDMA transport\n"); dprintk("\tsvcrdma_ord : %d\n", svcrdma_ord); - dprintk("\tmax_requests : %d\n", svcrdma_max_requests); - dprintk("\tsq_depth : %d\n", + dprintk("\tmax_requests : %u\n", svcrdma_max_requests); + dprintk("\tsq_depth : %u\n", svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT); + dprintk("\tmax_bc_requests : %u\n", svcrdma_max_bc_requests); dprintk("\tmax_inline : %d\n", svcrdma_max_req_size); svc_rdma_wq = alloc_workqueue("svc_rdma", 0, 0); @@ -264,39 +260,10 @@ int svc_rdma_init(void) svcrdma_table_header = register_sysctl_table(svcrdma_root_table); - /* Create the temporary map cache */ - svc_rdma_map_cachep = kmem_cache_create("svc_rdma_map_cache", - sizeof(struct svc_rdma_req_map), - 0, - SLAB_HWCACHE_ALIGN, - NULL); - if (!svc_rdma_map_cachep) { - printk(KERN_INFO "Could not allocate map cache.\n"); - goto err0; - } - - /* Create the temporary context cache */ - svc_rdma_ctxt_cachep = - kmem_cache_create("svc_rdma_ctxt_cache", - sizeof(struct svc_rdma_op_ctxt), - 0, - SLAB_HWCACHE_ALIGN, - NULL); - if (!svc_rdma_ctxt_cachep) { - printk(KERN_INFO "Could not allocate WR ctxt cache.\n"); - goto err1; - } - /* Register RDMA with the SVC transport switch */ svc_reg_xprt_class(&svc_rdma_class); #if defined(CONFIG_SUNRPC_BACKCHANNEL) svc_reg_xprt_class(&svc_rdma_bc_class); #endif return 0; - err1: - kmem_cache_destroy(svc_rdma_map_cachep); - err0: - unregister_sysctl_table(svcrdma_table_header); - destroy_workqueue(svc_rdma_wq); - return -ENOMEM; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c new file mode 100644 index 000000000000..65a7c232a345 --- /dev/null +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -0,0 +1,371 @@ +/* + * Copyright (c) 2015 Oracle. All rights reserved. + * + * Support for backward direction RPCs on RPC/RDMA (server-side). + */ + +#include <linux/sunrpc/svc_rdma.h> +#include "xprt_rdma.h" + +#define RPCDBG_FACILITY RPCDBG_SVCXPRT + +#undef SVCRDMA_BACKCHANNEL_DEBUG + +int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, struct rpcrdma_msg *rmsgp, + struct xdr_buf *rcvbuf) +{ + struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); + struct kvec *dst, *src = &rcvbuf->head[0]; + struct rpc_rqst *req; + unsigned long cwnd; + u32 credits; + size_t len; + __be32 xid; + __be32 *p; + int ret; + + p = (__be32 *)src->iov_base; + len = src->iov_len; + xid = rmsgp->rm_xid; + +#ifdef SVCRDMA_BACKCHANNEL_DEBUG + pr_info("%s: xid=%08x, length=%zu\n", + __func__, be32_to_cpu(xid), len); + pr_info("%s: RPC/RDMA: %*ph\n", + __func__, (int)RPCRDMA_HDRLEN_MIN, rmsgp); + pr_info("%s: RPC: %*ph\n", + __func__, (int)len, p); +#endif + + ret = -EAGAIN; + if (src->iov_len < 24) + goto out_shortreply; + + spin_lock_bh(&xprt->transport_lock); + req = xprt_lookup_rqst(xprt, xid); + if (!req) + goto out_notfound; + + dst = &req->rq_private_buf.head[0]; + memcpy(&req->rq_private_buf, &req->rq_rcv_buf, sizeof(struct xdr_buf)); + if (dst->iov_len < len) + goto out_unlock; + memcpy(dst->iov_base, p, len); + + credits = be32_to_cpu(rmsgp->rm_credit); + if (credits == 0) + credits = 1; /* don't deadlock */ + else if (credits > r_xprt->rx_buf.rb_bc_max_requests) + credits = r_xprt->rx_buf.rb_bc_max_requests; + + cwnd = xprt->cwnd; + xprt->cwnd = credits << RPC_CWNDSHIFT; + if (xprt->cwnd > cwnd) + xprt_release_rqst_cong(req->rq_task); + + ret = 0; + xprt_complete_rqst(req->rq_task, rcvbuf->len); + rcvbuf->len = 0; + +out_unlock: + spin_unlock_bh(&xprt->transport_lock); +out: + return ret; + +out_shortreply: + dprintk("svcrdma: short bc reply: xprt=%p, len=%zu\n", + xprt, src->iov_len); + goto out; + +out_notfound: + dprintk("svcrdma: unrecognized bc reply: xprt=%p, xid=%08x\n", + xprt, be32_to_cpu(xid)); + + goto out_unlock; +} + +/* Send a backwards direction RPC call. + * + * Caller holds the connection's mutex and has already marshaled + * the RPC/RDMA request. + * + * This is similar to svc_rdma_reply, but takes an rpc_rqst + * instead, does not support chunks, and avoids blocking memory + * allocation. + * + * XXX: There is still an opportunity to block in svc_rdma_send() + * if there are no SQ entries to post the Send. This may occur if + * the adapter has a small maximum SQ depth. + */ +static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma, + struct rpc_rqst *rqst) +{ + struct xdr_buf *sndbuf = &rqst->rq_snd_buf; + struct svc_rdma_op_ctxt *ctxt; + struct svc_rdma_req_map *vec; + struct ib_send_wr send_wr; + int ret; + + vec = svc_rdma_get_req_map(rdma); + ret = svc_rdma_map_xdr(rdma, sndbuf, vec); + if (ret) + goto out_err; + + /* Post a recv buffer to handle the reply for this request. */ + ret = svc_rdma_post_recv(rdma, GFP_NOIO); + if (ret) { + pr_err("svcrdma: Failed to post bc receive buffer, err=%d.\n", + ret); + pr_err("svcrdma: closing transport %p.\n", rdma); + set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); + ret = -ENOTCONN; + goto out_err; + } + + ctxt = svc_rdma_get_context(rdma); + ctxt->pages[0] = virt_to_page(rqst->rq_buffer); + ctxt->count = 1; + + ctxt->wr_op = IB_WR_SEND; + ctxt->direction = DMA_TO_DEVICE; + ctxt->sge[0].lkey = rdma->sc_pd->local_dma_lkey; + ctxt->sge[0].length = sndbuf->len; + ctxt->sge[0].addr = + ib_dma_map_page(rdma->sc_cm_id->device, ctxt->pages[0], 0, + sndbuf->len, DMA_TO_DEVICE); + if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr)) { + ret = -EIO; + goto out_unmap; + } + atomic_inc(&rdma->sc_dma_used); + + memset(&send_wr, 0, sizeof(send_wr)); + send_wr.wr_id = (unsigned long)ctxt; + send_wr.sg_list = ctxt->sge; + send_wr.num_sge = 1; + send_wr.opcode = IB_WR_SEND; + send_wr.send_flags = IB_SEND_SIGNALED; + + ret = svc_rdma_send(rdma, &send_wr); + if (ret) { + ret = -EIO; + goto out_unmap; + } + +out_err: + svc_rdma_put_req_map(rdma, vec); + dprintk("svcrdma: %s returns %d\n", __func__, ret); + return ret; + +out_unmap: + svc_rdma_unmap_dma(ctxt); + svc_rdma_put_context(ctxt, 1); + goto out_err; +} + +/* Server-side transport endpoint wants a whole page for its send + * buffer. The client RPC code constructs the RPC header in this + * buffer before it invokes ->send_request. + * + * Returns NULL if there was a temporary allocation failure. + */ +static void * +xprt_rdma_bc_allocate(struct rpc_task *task, size_t size) +{ + struct rpc_rqst *rqst = task->tk_rqstp; + struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt; + struct svcxprt_rdma *rdma; + struct page *page; + + rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt); + + /* Prevent an infinite loop: try to make this case work */ + if (size > PAGE_SIZE) + WARN_ONCE(1, "svcrdma: large bc buffer request (size %zu)\n", + size); + + page = alloc_page(RPCRDMA_DEF_GFP); + if (!page) + return NULL; + + return page_address(page); +} + +static void +xprt_rdma_bc_free(void *buffer) +{ + /* No-op: ctxt and page have already been freed. */ +} + +static int +rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst) +{ + struct rpc_xprt *xprt = rqst->rq_xprt; + struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); + struct rpcrdma_msg *headerp = (struct rpcrdma_msg *)rqst->rq_buffer; + int rc; + + /* Space in the send buffer for an RPC/RDMA header is reserved + * via xprt->tsh_size. + */ + headerp->rm_xid = rqst->rq_xid; + headerp->rm_vers = rpcrdma_version; + headerp->rm_credit = cpu_to_be32(r_xprt->rx_buf.rb_bc_max_requests); + headerp->rm_type = rdma_msg; + headerp->rm_body.rm_chunks[0] = xdr_zero; + headerp->rm_body.rm_chunks[1] = xdr_zero; + headerp->rm_body.rm_chunks[2] = xdr_zero; + +#ifdef SVCRDMA_BACKCHANNEL_DEBUG + pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer); +#endif + + rc = svc_rdma_bc_sendto(rdma, rqst); + if (rc) + goto drop_connection; + return rc; + +drop_connection: + dprintk("svcrdma: failed to send bc call\n"); + xprt_disconnect_done(xprt); + return -ENOTCONN; +} + +/* Send an RPC call on the passive end of a transport + * connection. + */ +static int +xprt_rdma_bc_send_request(struct rpc_task *task) +{ + struct rpc_rqst *rqst = task->tk_rqstp; + struct svc_xprt *sxprt = rqst->rq_xprt->bc_xprt; + struct svcxprt_rdma *rdma; + int ret; + + dprintk("svcrdma: sending bc call with xid: %08x\n", + be32_to_cpu(rqst->rq_xid)); + + if (!mutex_trylock(&sxprt->xpt_mutex)) { + rpc_sleep_on(&sxprt->xpt_bc_pending, task, NULL); + if (!mutex_trylock(&sxprt->xpt_mutex)) + return -EAGAIN; + rpc_wake_up_queued_task(&sxprt->xpt_bc_pending, task); + } + + ret = -ENOTCONN; + rdma = container_of(sxprt, struct svcxprt_rdma, sc_xprt); + if (!test_bit(XPT_DEAD, &sxprt->xpt_flags)) + ret = rpcrdma_bc_send_request(rdma, rqst); + + mutex_unlock(&sxprt->xpt_mutex); + + if (ret < 0) + return ret; + return 0; +} + +static void +xprt_rdma_bc_close(struct rpc_xprt *xprt) +{ + dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); +} + +static void +xprt_rdma_bc_put(struct rpc_xprt *xprt) +{ + dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); + + xprt_free(xprt); + module_put(THIS_MODULE); +} + +static struct rpc_xprt_ops xprt_rdma_bc_procs = { + .reserve_xprt = xprt_reserve_xprt_cong, + .release_xprt = xprt_release_xprt_cong, + .alloc_slot = xprt_alloc_slot, + .release_request = xprt_release_rqst_cong, + .buf_alloc = xprt_rdma_bc_allocate, + .buf_free = xprt_rdma_bc_free, + .send_request = xprt_rdma_bc_send_request, + .set_retrans_timeout = xprt_set_retrans_timeout_def, + .close = xprt_rdma_bc_close, + .destroy = xprt_rdma_bc_put, + .print_stats = xprt_rdma_print_stats +}; + +static const struct rpc_timeout xprt_rdma_bc_timeout = { + .to_initval = 60 * HZ, + .to_maxval = 60 * HZ, +}; + +/* It shouldn't matter if the number of backchannel session slots + * doesn't match the number of RPC/RDMA credits. That just means + * one or the other will have extra slots that aren't used. + */ +static struct rpc_xprt * +xprt_setup_rdma_bc(struct xprt_create *args) +{ + struct rpc_xprt *xprt; + struct rpcrdma_xprt *new_xprt; + + if (args->addrlen > sizeof(xprt->addr)) { + dprintk("RPC: %s: address too large\n", __func__); + return ERR_PTR(-EBADF); + } + + xprt = xprt_alloc(args->net, sizeof(*new_xprt), + RPCRDMA_MAX_BC_REQUESTS, + RPCRDMA_MAX_BC_REQUESTS); + if (!xprt) { + dprintk("RPC: %s: couldn't allocate rpc_xprt\n", + __func__); + return ERR_PTR(-ENOMEM); + } + + xprt->timeout = &xprt_rdma_bc_timeout; + xprt_set_bound(xprt); + xprt_set_connected(xprt); + xprt->bind_timeout = RPCRDMA_BIND_TO; + xprt->reestablish_timeout = RPCRDMA_INIT_REEST_TO; + xprt->idle_timeout = RPCRDMA_IDLE_DISC_TO; + + xprt->prot = XPRT_TRANSPORT_BC_RDMA; + xprt->tsh_size = RPCRDMA_HDRLEN_MIN / sizeof(__be32); + xprt->ops = &xprt_rdma_bc_procs; + + memcpy(&xprt->addr, args->dstaddr, args->addrlen); + xprt->addrlen = args->addrlen; + xprt_rdma_format_addresses(xprt, (struct sockaddr *)&xprt->addr); + xprt->resvport = 0; + + xprt->max_payload = xprt_rdma_max_inline_read; + + new_xprt = rpcx_to_rdmax(xprt); + new_xprt->rx_buf.rb_bc_max_requests = xprt->max_reqs; + + xprt_get(xprt); + args->bc_xprt->xpt_bc_xprt = xprt; + xprt->bc_xprt = args->bc_xprt; + + if (!try_module_get(THIS_MODULE)) + goto out_fail; + + /* Final put for backchannel xprt is in __svc_rdma_free */ + xprt_get(xprt); + return xprt; + +out_fail: + xprt_rdma_free_addresses(xprt); + args->bc_xprt->xpt_bc_xprt = NULL; + xprt_put(xprt); + xprt_free(xprt); + return ERR_PTR(-EINVAL); +} + +struct xprt_class xprt_rdma_bc = { + .list = LIST_HEAD_INIT(xprt_rdma_bc.list), + .name = "rdma backchannel", + .owner = THIS_MODULE, + .ident = XPRT_TRANSPORT_BC_RDMA, + .setup = xprt_setup_rdma_bc, +}; diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index ff4f01e527ec..c8b8a8b4181e 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -144,6 +144,7 @@ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, head->arg.pages[pg_no] = rqstp->rq_arg.pages[pg_no]; head->arg.page_len += len; + head->arg.len += len; if (!pg_off) head->count++; @@ -160,8 +161,7 @@ int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt, goto err; atomic_inc(&xprt->sc_dma_used); - /* The lkey here is either a local dma lkey or a dma_mr lkey */ - ctxt->sge[pno].lkey = xprt->sc_dma_lkey; + ctxt->sge[pno].lkey = xprt->sc_pd->local_dma_lkey; ctxt->sge[pno].length = len; ctxt->count++; @@ -567,6 +567,38 @@ static int rdma_read_complete(struct svc_rqst *rqstp, return ret; } +/* By convention, backchannel calls arrive via rdma_msg type + * messages, and never populate the chunk lists. This makes + * the RPC/RDMA header small and fixed in size, so it is + * straightforward to check the RPC header's direction field. + */ +static bool +svc_rdma_is_backchannel_reply(struct svc_xprt *xprt, struct rpcrdma_msg *rmsgp) +{ + __be32 *p = (__be32 *)rmsgp; + + if (!xprt->xpt_bc_xprt) + return false; + + if (rmsgp->rm_type != rdma_msg) + return false; + if (rmsgp->rm_body.rm_chunks[0] != xdr_zero) + return false; + if (rmsgp->rm_body.rm_chunks[1] != xdr_zero) + return false; + if (rmsgp->rm_body.rm_chunks[2] != xdr_zero) + return false; + + /* sanity */ + if (p[7] != rmsgp->rm_xid) + return false; + /* call direction */ + if (p[8] == cpu_to_be32(RPC_CALL)) + return false; + + return true; +} + /* * Set up the rqstp thread context to point to the RQ buffer. If * necessary, pull additional data from the client with an RDMA_READ @@ -632,6 +664,15 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) goto close_out; } + if (svc_rdma_is_backchannel_reply(xprt, rmsgp)) { + ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, rmsgp, + &rqstp->rq_arg); + svc_rdma_put_context(ctxt, 0); + if (ret) + goto repost; + return ret; + } + /* Read read-list data. */ ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt); if (ret > 0) { @@ -668,4 +709,15 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) set_bit(XPT_CLOSE, &xprt->xpt_flags); defer: return 0; + +repost: + ret = svc_rdma_post_recv(rdma_xprt, GFP_KERNEL); + if (ret) { + pr_err("svcrdma: could not post a receive buffer, err=%d.\n", + ret); + pr_err("svcrdma: closing transport %p.\n", rdma_xprt); + set_bit(XPT_CLOSE, &rdma_xprt->sc_xprt.xpt_flags); + ret = -ENOTCONN; + } + return ret; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 969a1ab75fc3..df57f3ce6cd2 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -50,9 +50,9 @@ #define RPCDBG_FACILITY RPCDBG_SVCXPRT -static int map_xdr(struct svcxprt_rdma *xprt, - struct xdr_buf *xdr, - struct svc_rdma_req_map *vec) +int svc_rdma_map_xdr(struct svcxprt_rdma *xprt, + struct xdr_buf *xdr, + struct svc_rdma_req_map *vec) { int sge_no; u32 sge_bytes; @@ -62,7 +62,7 @@ static int map_xdr(struct svcxprt_rdma *xprt, if (xdr->len != (xdr->head[0].iov_len + xdr->page_len + xdr->tail[0].iov_len)) { - pr_err("svcrdma: map_xdr: XDR buffer length error\n"); + pr_err("svcrdma: %s: XDR buffer length error\n", __func__); return -EIO; } @@ -97,9 +97,9 @@ static int map_xdr(struct svcxprt_rdma *xprt, sge_no++; } - dprintk("svcrdma: map_xdr: sge_no %d page_no %d " + dprintk("svcrdma: %s: sge_no %d page_no %d " "page_base %u page_len %u head_len %zu tail_len %zu\n", - sge_no, page_no, xdr->page_base, xdr->page_len, + __func__, sge_no, page_no, xdr->page_base, xdr->page_len, xdr->head[0].iov_len, xdr->tail[0].iov_len); vec->count = sge_no; @@ -265,7 +265,7 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp, sge[sge_no].addr)) goto err; atomic_inc(&xprt->sc_dma_used); - sge[sge_no].lkey = xprt->sc_dma_lkey; + sge[sge_no].lkey = xprt->sc_pd->local_dma_lkey; ctxt->count++; sge_off = 0; sge_no++; @@ -465,7 +465,7 @@ static int send_reply(struct svcxprt_rdma *rdma, int ret; /* Post a recv buffer to handle another request. */ - ret = svc_rdma_post_recv(rdma); + ret = svc_rdma_post_recv(rdma, GFP_KERNEL); if (ret) { printk(KERN_INFO "svcrdma: could not post a receive buffer, err=%d." @@ -480,7 +480,7 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->count = 1; /* Prepare the SGE for the RPCRDMA Header */ - ctxt->sge[0].lkey = rdma->sc_dma_lkey; + ctxt->sge[0].lkey = rdma->sc_pd->local_dma_lkey; ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp); ctxt->sge[0].addr = ib_dma_map_page(rdma->sc_cm_id->device, page, 0, @@ -504,7 +504,7 @@ static int send_reply(struct svcxprt_rdma *rdma, ctxt->sge[sge_no].addr)) goto err; atomic_inc(&rdma->sc_dma_used); - ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey; + ctxt->sge[sge_no].lkey = rdma->sc_pd->local_dma_lkey; ctxt->sge[sge_no].length = sge_bytes; } if (byte_count != 0) { @@ -591,14 +591,17 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) /* Build an req vec for the XDR */ ctxt = svc_rdma_get_context(rdma); ctxt->direction = DMA_TO_DEVICE; - vec = svc_rdma_get_req_map(); - ret = map_xdr(rdma, &rqstp->rq_res, vec); + vec = svc_rdma_get_req_map(rdma); + ret = svc_rdma_map_xdr(rdma, &rqstp->rq_res, vec); if (ret) goto err0; inline_bytes = rqstp->rq_res.len; /* Create the RDMA response header */ - res_page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); + ret = -ENOMEM; + res_page = alloc_page(GFP_KERNEL); + if (!res_page) + goto err0; rdma_resp = page_address(res_page); reply_ary = svc_rdma_get_reply_array(rdma_argp); if (reply_ary) @@ -630,14 +633,14 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) ret = send_reply(rdma, rqstp, res_page, rdma_resp, ctxt, vec, inline_bytes); - svc_rdma_put_req_map(vec); + svc_rdma_put_req_map(rdma, vec); dprintk("svcrdma: send_reply returns %d\n", ret); return ret; err1: put_page(res_page); err0: - svc_rdma_put_req_map(vec); + svc_rdma_put_req_map(rdma, vec); svc_rdma_put_context(ctxt, 0); return ret; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index b348b4adef29..5763825d09bf 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -153,18 +153,76 @@ static void svc_rdma_bc_free(struct svc_xprt *xprt) } #endif /* CONFIG_SUNRPC_BACKCHANNEL */ -struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) +static struct svc_rdma_op_ctxt *alloc_ctxt(struct svcxprt_rdma *xprt, + gfp_t flags) { struct svc_rdma_op_ctxt *ctxt; - ctxt = kmem_cache_alloc(svc_rdma_ctxt_cachep, - GFP_KERNEL | __GFP_NOFAIL); - ctxt->xprt = xprt; - INIT_LIST_HEAD(&ctxt->dto_q); + ctxt = kmalloc(sizeof(*ctxt), flags); + if (ctxt) { + ctxt->xprt = xprt; + INIT_LIST_HEAD(&ctxt->free); + INIT_LIST_HEAD(&ctxt->dto_q); + } + return ctxt; +} + +static bool svc_rdma_prealloc_ctxts(struct svcxprt_rdma *xprt) +{ + unsigned int i; + + /* Each RPC/RDMA credit can consume a number of send + * and receive WQEs. One ctxt is allocated for each. + */ + i = xprt->sc_sq_depth + xprt->sc_rq_depth; + + while (i--) { + struct svc_rdma_op_ctxt *ctxt; + + ctxt = alloc_ctxt(xprt, GFP_KERNEL); + if (!ctxt) { + dprintk("svcrdma: No memory for RDMA ctxt\n"); + return false; + } + list_add(&ctxt->free, &xprt->sc_ctxts); + } + return true; +} + +struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *xprt) +{ + struct svc_rdma_op_ctxt *ctxt = NULL; + + spin_lock_bh(&xprt->sc_ctxt_lock); + xprt->sc_ctxt_used++; + if (list_empty(&xprt->sc_ctxts)) + goto out_empty; + + ctxt = list_first_entry(&xprt->sc_ctxts, + struct svc_rdma_op_ctxt, free); + list_del_init(&ctxt->free); + spin_unlock_bh(&xprt->sc_ctxt_lock); + +out: ctxt->count = 0; ctxt->frmr = NULL; - atomic_inc(&xprt->sc_ctxt_used); return ctxt; + +out_empty: + /* Either pre-allocation missed the mark, or send + * queue accounting is broken. + */ + spin_unlock_bh(&xprt->sc_ctxt_lock); + + ctxt = alloc_ctxt(xprt, GFP_NOIO); + if (ctxt) + goto out; + + spin_lock_bh(&xprt->sc_ctxt_lock); + xprt->sc_ctxt_used--; + spin_unlock_bh(&xprt->sc_ctxt_lock); + WARN_ONCE(1, "svcrdma: empty RDMA ctxt list?\n"); + return NULL; } void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) @@ -174,11 +232,11 @@ void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) for (i = 0; i < ctxt->count && ctxt->sge[i].length; i++) { /* * Unmap the DMA addr in the SGE if the lkey matches - * the sc_dma_lkey, otherwise, ignore it since it is + * the local_dma_lkey, otherwise, ignore it since it is * an FRMR lkey and will be unmapped later when the * last WR that uses it completes. */ - if (ctxt->sge[i].lkey == xprt->sc_dma_lkey) { + if (ctxt->sge[i].lkey == xprt->sc_pd->local_dma_lkey) { atomic_dec(&xprt->sc_dma_used); ib_dma_unmap_page(xprt->sc_cm_id->device, ctxt->sge[i].addr, @@ -190,35 +248,108 @@ void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt) void svc_rdma_put_context(struct svc_rdma_op_ctxt *ctxt, int free_pages) { - struct svcxprt_rdma *xprt; + struct svcxprt_rdma *xprt = ctxt->xprt; int i; - xprt = ctxt->xprt; if (free_pages) for (i = 0; i < ctxt->count; i++) put_page(ctxt->pages[i]); - kmem_cache_free(svc_rdma_ctxt_cachep, ctxt); - atomic_dec(&xprt->sc_ctxt_used); + spin_lock_bh(&xprt->sc_ctxt_lock); + xprt->sc_ctxt_used--; + list_add(&ctxt->free, &xprt->sc_ctxts); + spin_unlock_bh(&xprt->sc_ctxt_lock); } -/* - * Temporary NFS req mappings are shared across all transport - * instances. These are short lived and should be bounded by the number - * of concurrent server threads * depth of the SQ. - */ -struct svc_rdma_req_map *svc_rdma_get_req_map(void) +static void svc_rdma_destroy_ctxts(struct svcxprt_rdma *xprt) +{ + while (!list_empty(&xprt->sc_ctxts)) { + struct svc_rdma_op_ctxt *ctxt; + + ctxt = list_first_entry(&xprt->sc_ctxts, + struct svc_rdma_op_ctxt, free); + list_del(&ctxt->free); + kfree(ctxt); + } +} + +static struct svc_rdma_req_map *alloc_req_map(gfp_t flags) { struct svc_rdma_req_map *map; - map = kmem_cache_alloc(svc_rdma_map_cachep, - GFP_KERNEL | __GFP_NOFAIL); + + map = kmalloc(sizeof(*map), flags); + if (map) + INIT_LIST_HEAD(&map->free); + return map; +} + +static bool svc_rdma_prealloc_maps(struct svcxprt_rdma *xprt) +{ + unsigned int i; + + /* One for each receive buffer on this connection. */ + i = xprt->sc_max_requests; + + while (i--) { + struct svc_rdma_req_map *map; + + map = alloc_req_map(GFP_KERNEL); + if (!map) { + dprintk("svcrdma: No memory for request map\n"); + return false; + } + list_add(&map->free, &xprt->sc_maps); + } + return true; +} + +struct svc_rdma_req_map *svc_rdma_get_req_map(struct svcxprt_rdma *xprt) +{ + struct svc_rdma_req_map *map = NULL; + + spin_lock(&xprt->sc_map_lock); + if (list_empty(&xprt->sc_maps)) + goto out_empty; + + map = list_first_entry(&xprt->sc_maps, + struct svc_rdma_req_map, free); + list_del_init(&map->free); + spin_unlock(&xprt->sc_map_lock); + +out: map->count = 0; return map; + +out_empty: + spin_unlock(&xprt->sc_map_lock); + + /* Pre-allocation amount was incorrect */ + map = alloc_req_map(GFP_NOIO); + if (map) + goto out; + + WARN_ONCE(1, "svcrdma: empty request map list?\n"); + return NULL; +} + +void svc_rdma_put_req_map(struct svcxprt_rdma *xprt, + struct svc_rdma_req_map *map) +{ + spin_lock(&xprt->sc_map_lock); + list_add(&map->free, &xprt->sc_maps); + spin_unlock(&xprt->sc_map_lock); } -void svc_rdma_put_req_map(struct svc_rdma_req_map *map) +static void svc_rdma_destroy_maps(struct svcxprt_rdma *xprt) { - kmem_cache_free(svc_rdma_map_cachep, map); + while (!list_empty(&xprt->sc_maps)) { + struct svc_rdma_req_map *map; + + map = list_first_entry(&xprt->sc_maps, + struct svc_rdma_req_map, free); + list_del(&map->free); + kfree(map); + } } /* ib_cq event handler */ @@ -386,46 +517,44 @@ static void rq_cq_reap(struct svcxprt_rdma *xprt) static void process_context(struct svcxprt_rdma *xprt, struct svc_rdma_op_ctxt *ctxt) { + struct svc_rdma_op_ctxt *read_hdr; + int free_pages = 0; + svc_rdma_unmap_dma(ctxt); switch (ctxt->wr_op) { case IB_WR_SEND: - if (ctxt->frmr) - pr_err("svcrdma: SEND: ctxt->frmr != NULL\n"); - svc_rdma_put_context(ctxt, 1); + free_pages = 1; break; case IB_WR_RDMA_WRITE: - if (ctxt->frmr) - pr_err("svcrdma: WRITE: ctxt->frmr != NULL\n"); - svc_rdma_put_context(ctxt, 0); break; case IB_WR_RDMA_READ: case IB_WR_RDMA_READ_WITH_INV: svc_rdma_put_frmr(xprt, ctxt->frmr); - if (test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) { - struct svc_rdma_op_ctxt *read_hdr = ctxt->read_hdr; - if (read_hdr) { - spin_lock_bh(&xprt->sc_rq_dto_lock); - set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); - list_add_tail(&read_hdr->dto_q, - &xprt->sc_read_complete_q); - spin_unlock_bh(&xprt->sc_rq_dto_lock); - } else { - pr_err("svcrdma: ctxt->read_hdr == NULL\n"); - } - svc_xprt_enqueue(&xprt->sc_xprt); - } + + if (!test_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags)) + break; + + read_hdr = ctxt->read_hdr; svc_rdma_put_context(ctxt, 0); - break; + + spin_lock_bh(&xprt->sc_rq_dto_lock); + set_bit(XPT_DATA, &xprt->sc_xprt.xpt_flags); + list_add_tail(&read_hdr->dto_q, + &xprt->sc_read_complete_q); + spin_unlock_bh(&xprt->sc_rq_dto_lock); + svc_xprt_enqueue(&xprt->sc_xprt); + return; default: - printk(KERN_ERR "svcrdma: unexpected completion type, " - "opcode=%d\n", - ctxt->wr_op); + dprintk("svcrdma: unexpected completion opcode=%d\n", + ctxt->wr_op); break; } + + svc_rdma_put_context(ctxt, free_pages); } /* @@ -523,19 +652,15 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, INIT_LIST_HEAD(&cma_xprt->sc_rq_dto_q); INIT_LIST_HEAD(&cma_xprt->sc_read_complete_q); INIT_LIST_HEAD(&cma_xprt->sc_frmr_q); + INIT_LIST_HEAD(&cma_xprt->sc_ctxts); + INIT_LIST_HEAD(&cma_xprt->sc_maps); init_waitqueue_head(&cma_xprt->sc_send_wait); spin_lock_init(&cma_xprt->sc_lock); spin_lock_init(&cma_xprt->sc_rq_dto_lock); spin_lock_init(&cma_xprt->sc_frmr_q_lock); - - cma_xprt->sc_ord = svcrdma_ord; - - cma_xprt->sc_max_req_size = svcrdma_max_req_size; - cma_xprt->sc_max_requests = svcrdma_max_requests; - cma_xprt->sc_sq_depth = svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT; - atomic_set(&cma_xprt->sc_sq_count, 0); - atomic_set(&cma_xprt->sc_ctxt_used, 0); + spin_lock_init(&cma_xprt->sc_ctxt_lock); + spin_lock_init(&cma_xprt->sc_map_lock); if (listener) set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags); @@ -543,7 +668,7 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv, return cma_xprt; } -int svc_rdma_post_recv(struct svcxprt_rdma *xprt) +int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags) { struct ib_recv_wr recv_wr, *bad_recv_wr; struct svc_rdma_op_ctxt *ctxt; @@ -561,7 +686,9 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) pr_err("svcrdma: Too many sges (%d)\n", sge_no); goto err_put_ctxt; } - page = alloc_page(GFP_KERNEL | __GFP_NOFAIL); + page = alloc_page(flags); + if (!page) + goto err_put_ctxt; ctxt->pages[sge_no] = page; pa = ib_dma_map_page(xprt->sc_cm_id->device, page, 0, PAGE_SIZE, @@ -571,7 +698,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt) atomic_inc(&xprt->sc_dma_used); ctxt->sge[sge_no].addr = pa; ctxt->sge[sge_no].length = PAGE_SIZE; - ctxt->sge[sge_no].lkey = xprt->sc_dma_lkey; + ctxt->sge[sge_no].lkey = xprt->sc_pd->local_dma_lkey; ctxt->count = sge_no + 1; buflen += PAGE_SIZE; } @@ -886,11 +1013,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) 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 = 0; - int ret; - int i; + struct ib_device *dev; + unsigned int i; + int ret = 0; listen_rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt); clear_bit(XPT_CONN, &xprt->xpt_flags); @@ -910,37 +1035,42 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) dprintk("svcrdma: newxprt from accept queue = %p, cm_id=%p\n", newxprt, newxprt->sc_cm_id); - ret = ib_query_device(newxprt->sc_cm_id->device, &devattr); - if (ret) { - dprintk("svcrdma: could not query device attributes on " - "device %p, rc=%d\n", newxprt->sc_cm_id->device, ret); - goto errout; - } + dev = newxprt->sc_cm_id->device; /* Qualify the transport resource defaults with the * capabilities of this particular device */ - newxprt->sc_max_sge = min((size_t)devattr.max_sge, + newxprt->sc_max_sge = min((size_t)dev->attrs.max_sge, (size_t)RPCSVC_MAXPAGES); - newxprt->sc_max_sge_rd = min_t(size_t, devattr.max_sge_rd, + newxprt->sc_max_sge_rd = min_t(size_t, dev->attrs.max_sge_rd, RPCSVC_MAXPAGES); - newxprt->sc_max_requests = min((size_t)devattr.max_qp_wr, - (size_t)svcrdma_max_requests); - newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests; + newxprt->sc_max_req_size = svcrdma_max_req_size; + newxprt->sc_max_requests = min_t(u32, dev->attrs.max_qp_wr, + svcrdma_max_requests); + newxprt->sc_max_bc_requests = min_t(u32, dev->attrs.max_qp_wr, + svcrdma_max_bc_requests); + newxprt->sc_rq_depth = newxprt->sc_max_requests + + newxprt->sc_max_bc_requests; + newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_rq_depth; + + if (!svc_rdma_prealloc_ctxts(newxprt)) + goto errout; + if (!svc_rdma_prealloc_maps(newxprt)) + goto errout; /* * Limit ORD based on client limit, local device limit, and * configured svcrdma limit. */ - newxprt->sc_ord = min_t(size_t, devattr.max_qp_rd_atom, newxprt->sc_ord); + newxprt->sc_ord = min_t(size_t, dev->attrs.max_qp_rd_atom, newxprt->sc_ord); newxprt->sc_ord = min_t(size_t, svcrdma_ord, newxprt->sc_ord); - newxprt->sc_pd = ib_alloc_pd(newxprt->sc_cm_id->device); + newxprt->sc_pd = ib_alloc_pd(dev); if (IS_ERR(newxprt->sc_pd)) { 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, + newxprt->sc_sq_cq = ib_create_cq(dev, sq_comp_handler, cq_event_handler, newxprt, @@ -949,8 +1079,8 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) 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, + cq_attr.cqe = newxprt->sc_rq_depth; + newxprt->sc_rq_cq = ib_create_cq(dev, rq_comp_handler, cq_event_handler, newxprt, @@ -964,7 +1094,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) qp_attr.event_handler = qp_event_handler; qp_attr.qp_context = &newxprt->sc_xprt; qp_attr.cap.max_send_wr = newxprt->sc_sq_depth; - qp_attr.cap.max_recv_wr = newxprt->sc_max_requests; + qp_attr.cap.max_recv_wr = newxprt->sc_rq_depth; qp_attr.cap.max_send_sge = newxprt->sc_max_sge; qp_attr.cap.max_recv_sge = newxprt->sc_max_sge; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; @@ -978,7 +1108,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) " cap.max_send_sge = %d\n" " cap.max_recv_sge = %d\n", newxprt->sc_cm_id, newxprt->sc_pd, - newxprt->sc_cm_id->device, newxprt->sc_pd->device, + dev, newxprt->sc_pd->device, qp_attr.cap.max_send_wr, qp_attr.cap.max_recv_wr, qp_attr.cap.max_send_sge, @@ -1014,9 +1144,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) * of an RDMA_READ. IB does not. */ newxprt->sc_reader = rdma_read_chunk_lcl; - if (devattr.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { + if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) { newxprt->sc_frmr_pg_list_len = - devattr.max_fast_reg_page_list_len; + dev->attrs.max_fast_reg_page_list_len; newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG; newxprt->sc_reader = rdma_read_chunk_frmr; } @@ -1024,44 +1154,16 @@ 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 */ - 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)) + if (!rdma_protocol_iwarp(dev, newxprt->sc_cm_id->port_num) && + !rdma_ib_or_roce(dev, 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)) + if (rdma_protocol_iwarp(dev, 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 */ - newxprt->sc_phys_mr = - ib_get_dma_mr(newxprt->sc_pd, dma_mr_acc); - if (IS_ERR(newxprt->sc_phys_mr)) { - dprintk("svcrdma: Failed to create DMA MR ret=%d\n", - ret); - goto errout; - } - newxprt->sc_dma_lkey = newxprt->sc_phys_mr->lkey; - } else - newxprt->sc_dma_lkey = - newxprt->sc_cm_id->device->local_dma_lkey; - /* Post receive buffers */ - for (i = 0; i < newxprt->sc_max_requests; i++) { - ret = svc_rdma_post_recv(newxprt); + for (i = 0; i < newxprt->sc_rq_depth; i++) { + ret = svc_rdma_post_recv(newxprt, GFP_KERNEL); if (ret) { dprintk("svcrdma: failure posting receive buffers\n"); goto errout; @@ -1160,12 +1262,14 @@ static void __svc_rdma_free(struct work_struct *work) { struct svcxprt_rdma *rdma = container_of(work, struct svcxprt_rdma, sc_work); - dprintk("svcrdma: svc_rdma_free(%p)\n", rdma); + struct svc_xprt *xprt = &rdma->sc_xprt; + + dprintk("svcrdma: %s(%p)\n", __func__, rdma); /* We should only be called from kref_put */ - if (atomic_read(&rdma->sc_xprt.xpt_ref.refcount) != 0) + if (atomic_read(&xprt->xpt_ref.refcount) != 0) pr_err("svcrdma: sc_xprt still in use? (%d)\n", - atomic_read(&rdma->sc_xprt.xpt_ref.refcount)); + atomic_read(&xprt->xpt_ref.refcount)); /* * Destroy queued, but not processed read completions. Note @@ -1193,15 +1297,22 @@ static void __svc_rdma_free(struct work_struct *work) } /* Warn if we leaked a resource or under-referenced */ - if (atomic_read(&rdma->sc_ctxt_used) != 0) + if (rdma->sc_ctxt_used != 0) pr_err("svcrdma: ctxt still in use? (%d)\n", - atomic_read(&rdma->sc_ctxt_used)); + rdma->sc_ctxt_used); if (atomic_read(&rdma->sc_dma_used) != 0) pr_err("svcrdma: dma still in use? (%d)\n", atomic_read(&rdma->sc_dma_used)); - /* De-allocate fastreg mr */ + /* Final put of backchannel client transport */ + if (xprt->xpt_bc_xprt) { + xprt_put(xprt->xpt_bc_xprt); + xprt->xpt_bc_xprt = NULL; + } + rdma_dealloc_frmr_q(rdma); + svc_rdma_destroy_ctxts(rdma); + svc_rdma_destroy_maps(rdma); /* Destroy the QP if present (not a listener) */ if (rdma->sc_qp && !IS_ERR(rdma->sc_qp)) @@ -1213,9 +1324,6 @@ static void __svc_rdma_free(struct work_struct *work) if (rdma->sc_rq_cq && !IS_ERR(rdma->sc_rq_cq)) ib_destroy_cq(rdma->sc_rq_cq); - if (rdma->sc_phys_mr && !IS_ERR(rdma->sc_phys_mr)) - ib_dereg_mr(rdma->sc_phys_mr); - if (rdma->sc_pd && !IS_ERR(rdma->sc_pd)) ib_dealloc_pd(rdma->sc_pd); @@ -1321,7 +1429,9 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, int length; int ret; - p = alloc_page(GFP_KERNEL | __GFP_NOFAIL); + p = alloc_page(GFP_KERNEL); + if (!p) + return; va = page_address(p); /* XDR encode error */ @@ -1341,7 +1451,7 @@ void svc_rdma_send_error(struct svcxprt_rdma *xprt, struct rpcrdma_msg *rmsgp, return; } atomic_inc(&xprt->sc_dma_used); - ctxt->sge[0].lkey = xprt->sc_dma_lkey; + ctxt->sge[0].lkey = xprt->sc_pd->local_dma_lkey; ctxt->sge[0].length = length; /* Prepare SEND WR */ diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c index 740bddcf3488..b1b009f10ea3 100644 --- a/net/sunrpc/xprtrdma/transport.c +++ b/net/sunrpc/xprtrdma/transport.c @@ -63,7 +63,7 @@ */ static unsigned int xprt_rdma_slot_table_entries = RPCRDMA_DEF_SLOT_TABLE; -static unsigned int xprt_rdma_max_inline_read = RPCRDMA_DEF_INLINE; +unsigned int xprt_rdma_max_inline_read = RPCRDMA_DEF_INLINE; static unsigned int xprt_rdma_max_inline_write = RPCRDMA_DEF_INLINE; static unsigned int xprt_rdma_inline_write_padding; static unsigned int xprt_rdma_memreg_strategy = RPCRDMA_FRMR; @@ -143,12 +143,7 @@ static struct ctl_table sunrpc_table[] = { #endif -#define RPCRDMA_BIND_TO (60U * HZ) -#define RPCRDMA_INIT_REEST_TO (5U * HZ) -#define RPCRDMA_MAX_REEST_TO (30U * HZ) -#define RPCRDMA_IDLE_DISC_TO (5U * 60 * HZ) - -static struct rpc_xprt_ops xprt_rdma_procs; /* forward reference */ +static struct rpc_xprt_ops xprt_rdma_procs; /*forward reference */ static void xprt_rdma_format_addresses4(struct rpc_xprt *xprt, struct sockaddr *sap) @@ -174,7 +169,7 @@ xprt_rdma_format_addresses6(struct rpc_xprt *xprt, struct sockaddr *sap) xprt->address_strings[RPC_DISPLAY_NETID] = RPCBIND_NETID_RDMA6; } -static void +void xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap) { char buf[128]; @@ -203,7 +198,7 @@ xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap) xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma"; } -static void +void xprt_rdma_free_addresses(struct rpc_xprt *xprt) { unsigned int i; @@ -499,7 +494,7 @@ xprt_rdma_allocate(struct rpc_task *task, size_t size) if (req == NULL) return NULL; - flags = GFP_NOIO | __GFP_NOWARN; + flags = RPCRDMA_DEF_GFP; if (RPC_IS_SWAPPER(task)) flags = __GFP_MEMALLOC | GFP_NOWAIT | __GFP_NOWARN; @@ -642,7 +637,7 @@ drop_connection: return -ENOTCONN; /* implies disconnect */ } -static void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) +void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq) { struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt); long idle_time = 0; @@ -743,6 +738,11 @@ void xprt_rdma_cleanup(void) rpcrdma_destroy_wq(); frwr_destroy_recovery_wq(); + + rc = xprt_unregister_transport(&xprt_rdma_bc); + if (rc) + dprintk("RPC: %s: xprt_unregister(bc) returned %i\n", + __func__, rc); } int xprt_rdma_init(void) @@ -766,6 +766,14 @@ int xprt_rdma_init(void) return rc; } + rc = xprt_register_transport(&xprt_rdma_bc); + if (rc) { + xprt_unregister_transport(&xprt_rdma); + rpcrdma_destroy_wq(); + frwr_destroy_recovery_wq(); + return rc; + } + dprintk("RPCRDMA Module Init, register RPC RDMA transport\n"); dprintk("Defaults:\n"); diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 732c71ce5dca..878f1bfb1db9 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -462,7 +462,6 @@ int rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) { struct rpcrdma_ia *ia = &xprt->rx_ia; - struct ib_device_attr *devattr = &ia->ri_devattr; int rc; ia->ri_dma_mr = NULL; @@ -482,16 +481,10 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg) goto out2; } - rc = ib_query_device(ia->ri_device, devattr); - if (rc) { - dprintk("RPC: %s: ib_query_device failed %d\n", - __func__, rc); - goto out3; - } - if (memreg == RPCRDMA_FRMR) { - if (!(devattr->device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) || - (devattr->max_fast_reg_page_list_len == 0)) { + if (!(ia->ri_device->attrs.device_cap_flags & + IB_DEVICE_MEM_MGT_EXTENSIONS) || + (ia->ri_device->attrs.max_fast_reg_page_list_len == 0)) { dprintk("RPC: %s: FRMR registration " "not supported by HCA\n", __func__); memreg = RPCRDMA_MTHCAFMR; @@ -566,24 +559,23 @@ int rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, struct rpcrdma_create_data_internal *cdata) { - struct ib_device_attr *devattr = &ia->ri_devattr; struct ib_cq *sendcq, *recvcq; struct ib_cq_init_attr cq_attr = {}; unsigned int max_qp_wr; int rc, err; - if (devattr->max_sge < RPCRDMA_MAX_IOVS) { + if (ia->ri_device->attrs.max_sge < RPCRDMA_MAX_IOVS) { dprintk("RPC: %s: insufficient sge's available\n", __func__); return -ENOMEM; } - if (devattr->max_qp_wr <= RPCRDMA_BACKWARD_WRS) { + if (ia->ri_device->attrs.max_qp_wr <= RPCRDMA_BACKWARD_WRS) { dprintk("RPC: %s: insufficient wqe's available\n", __func__); return -ENOMEM; } - max_qp_wr = devattr->max_qp_wr - RPCRDMA_BACKWARD_WRS; + max_qp_wr = ia->ri_device->attrs.max_qp_wr - RPCRDMA_BACKWARD_WRS; /* check provider's send/recv wr limits */ if (cdata->max_requests > max_qp_wr) @@ -668,11 +660,11 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia, /* Client offers RDMA Read but does not initiate */ ep->rep_remote_cma.initiator_depth = 0; - if (devattr->max_qp_rd_atom > 32) /* arbitrary but <= 255 */ + if (ia->ri_device->attrs.max_qp_rd_atom > 32) /* arbitrary but <= 255 */ ep->rep_remote_cma.responder_resources = 32; else ep->rep_remote_cma.responder_resources = - devattr->max_qp_rd_atom; + ia->ri_device->attrs.max_qp_rd_atom; ep->rep_remote_cma.retry_count = 7; ep->rep_remote_cma.flow_control = 0; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 728101ddc44b..38fe11b09875 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -55,6 +55,11 @@ #define RDMA_RESOLVE_TIMEOUT (5000) /* 5 seconds */ #define RDMA_CONNECT_RETRY_MAX (2) /* retries if no listener backlog */ +#define RPCRDMA_BIND_TO (60U * HZ) +#define RPCRDMA_INIT_REEST_TO (5U * HZ) +#define RPCRDMA_MAX_REEST_TO (30U * HZ) +#define RPCRDMA_IDLE_DISC_TO (5U * 60 * HZ) + /* * Interface Adapter -- one per transport instance */ @@ -68,7 +73,6 @@ struct rpcrdma_ia { struct completion ri_done; int ri_async_rc; unsigned int ri_max_frmr_depth; - struct ib_device_attr ri_devattr; struct ib_qp_attr ri_qp_attr; struct ib_qp_init_attr ri_qp_init_attr; }; @@ -142,6 +146,8 @@ rdmab_to_msg(struct rpcrdma_regbuf *rb) return (struct rpcrdma_msg *)rb->rg_base; } +#define RPCRDMA_DEF_GFP (GFP_NOIO | __GFP_NOWARN) + /* * struct rpcrdma_rep -- this structure encapsulates state required to recv * and complete a reply, asychronously. It needs several pieces of @@ -309,6 +315,8 @@ struct rpcrdma_buffer { u32 rb_bc_srv_max_requests; spinlock_t rb_reqslock; /* protect rb_allreqs */ struct list_head rb_allreqs; + + u32 rb_bc_max_requests; }; #define rdmab_to_ia(b) (&container_of((b), struct rpcrdma_xprt, rx_buf)->rx_ia) @@ -516,6 +524,10 @@ int rpcrdma_marshal_req(struct rpc_rqst *); /* RPC/RDMA module init - xprtrdma/transport.c */ +extern unsigned int xprt_rdma_max_inline_read; +void xprt_rdma_format_addresses(struct rpc_xprt *xprt, struct sockaddr *sap); +void xprt_rdma_free_addresses(struct rpc_xprt *xprt); +void xprt_rdma_print_stats(struct rpc_xprt *xprt, struct seq_file *seq); int xprt_rdma_init(void); void xprt_rdma_cleanup(void); @@ -531,11 +543,6 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *); void xprt_rdma_bc_destroy(struct rpc_xprt *, unsigned int); #endif /* CONFIG_SUNRPC_BACKCHANNEL */ -/* 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 */ -extern struct kmem_cache *svc_rdma_ctxt_cachep; -/* Workqueue created in svc_rdma.c */ -extern struct workqueue_struct *svc_rdma_wq; +extern struct xprt_class xprt_rdma_bc; #endif /* _LINUX_SUNRPC_XPRT_RDMA_H */ |