svcrdma: Add class for RDMA backwards direction transport

To support the server-side of an NFSv4.1 backchannel on RDMA
connections, add a transport class that enables backward
direction messages on an existing forward channel connection.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Acked-by: Bruce Fields <bfields@fieldses.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
This commit is contained in:
Chuck Lever 2016-01-07 14:50:10 -05:00 committed by Doug Ledford
parent 03fe993153
commit 5d252f90a8
8 changed files with 475 additions and 15 deletions

View File

@ -195,6 +195,11 @@ struct svcxprt_rdma {
#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD
/* svc_rdma_backchannel.c */
extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
struct rpcrdma_msg *rmsgp,
struct xdr_buf *rcvbuf);
/* svc_rdma_marshal.c */
extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *);
extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,

View File

@ -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);

View File

@ -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

View File

@ -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_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,
};

View File

@ -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;
}

View File

@ -1287,12 +1287,14 @@ 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
@ -1327,6 +1329,12 @@ static void __svc_rdma_free(struct work_struct *work)
pr_err("svcrdma: dma still in use? (%d)\n",
atomic_read(&rdma->sc_dma_used));
/* 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);

View File

@ -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;
@ -639,7 +634,7 @@ 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;
@ -740,6 +735,11 @@ 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)
@ -763,6 +763,14 @@ 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");

View File

@ -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
*/
@ -147,6 +152,8 @@ 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
@ -308,6 +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)
@ -513,6 +522,10 @@ 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);
@ -528,4 +541,6 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *);
void xprt_rdma_bc_destroy(struct rpc_xprt *, unsigned int);
#endif /* CONFIG_SUNRPC_BACKCHANNEL */
extern struct xprt_class xprt_rdma_bc;
#endif /* _LINUX_SUNRPC_XPRT_RDMA_H */