* [PATCH v5 01/10] svcrdma: Clean up rdma_create_xprt()
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
@ 2016-01-07 19:48 ` Chuck Lever
2016-01-07 19:49 ` [PATCH v5 02/10] svcrdma: Clean up process_context() Chuck Lever
` (9 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:48 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
kzalloc is used here, so setting the atomic fields to zero is
unnecessary. sc_ord is set again in handle_connect_req. The other
fields are re-initialized in svc_rdma_accept().
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
net/sunrpc/xprtrdma/svc_rdma_transport.c | 9 +--------
1 file changed, 1 insertion(+), 8 deletions(-)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 4d695af..45d1824 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -529,14 +529,6 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
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);
-
if (listener)
set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags);
@@ -918,6 +910,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
(size_t)RPCSVC_MAXPAGES);
newxprt->sc_max_sge_rd = min_t(size_t, dev->attrs.max_sge_rd,
RPCSVC_MAXPAGES);
+ newxprt->sc_max_req_size = svcrdma_max_req_size;
newxprt->sc_max_requests = min((size_t)dev->attrs.max_qp_wr,
(size_t)svcrdma_max_requests);
newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests;
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 02/10] svcrdma: Clean up process_context()
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
2016-01-07 19:48 ` [PATCH v5 01/10] svcrdma: Clean up rdma_create_xprt() Chuck Lever
@ 2016-01-07 19:49 ` Chuck Lever
2016-01-07 19:49 ` [PATCH v5 03/10] svcrdma: Improve allocation of struct svc_rdma_op_ctxt Chuck Lever
` (8 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:49 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
Be sure the completed ctxt is put in every path.
The xprt enqueue can take a while, so put the completed ctxt back
in circulation _before_ enqueuing the xprt.
Remove/disable debugging.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
net/sunrpc/xprtrdma/svc_rdma_transport.c | 44 ++++++++++++++----------------
1 file changed, 21 insertions(+), 23 deletions(-)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 45d1824..a100d56 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -386,46 +386,44 @@ 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);
}
/*
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 03/10] svcrdma: Improve allocation of struct svc_rdma_op_ctxt
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
2016-01-07 19:48 ` [PATCH v5 01/10] svcrdma: Clean up rdma_create_xprt() Chuck Lever
2016-01-07 19:49 ` [PATCH v5 02/10] svcrdma: Clean up process_context() Chuck Lever
@ 2016-01-07 19:49 ` Chuck Lever
2016-01-07 19:49 ` [PATCH v5 04/10] svcrdma: Improve allocation of struct svc_rdma_req_map Chuck Lever
` (7 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:49 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
When the maximum payload size of NFS READ and WRITE was increased
by commit cc9a903d915c ("svcrdma: Change maximum server payload back
to RPCSVC_MAXPAYLOAD"), the size of struct svc_rdma_op_ctxt
increased to over 6KB (on x86_64). That makes allocating one of
these from a kmem_cache more likely to fail in situations when
system memory is exhausted.
Since I'm about to add a caller where this allocation must always
work _and_ it cannot sleep, pre-allocate ctxts for each connection.
Another motivation for this change is that NFSv4.x servers are
required by specification not to drop NFS requests. Pre-allocating
memory resources reduces the likelihood of a drop.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 6 +-
net/sunrpc/xprtrdma/svc_rdma_transport.c | 102 ++++++++++++++++++++++++++----
2 files changed, 94 insertions(+), 14 deletions(-)
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index f869807..be2804b 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -69,6 +69,7 @@ extern atomic_t rdma_stat_sq_prod;
* completes.
*/
struct svc_rdma_op_ctxt {
+ struct list_head free;
struct svc_rdma_op_ctxt *read_hdr;
struct svc_rdma_fastreg_mr *frmr;
int hdr_count;
@@ -141,7 +142,10 @@ struct svcxprt_rdma {
struct ib_pd *sc_pd;
atomic_t sc_dma_used;
- atomic_t sc_ctxt_used;
+ spinlock_t sc_ctxt_lock;
+ struct list_head sc_ctxts;
+ int sc_ctxt_used;
+
struct list_head sc_rq_dto_q;
spinlock_t sc_rq_dto_lock;
struct ib_qp *sc_qp;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index a100d56..9801115 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)
+{
+ 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_max_requests;
+
+ 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)
@@ -190,16 +248,29 @@ 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);
+}
+
+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);
+ }
}
/*
@@ -521,11 +592,13 @@ 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_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);
+ spin_lock_init(&cma_xprt->sc_ctxt_lock);
if (listener)
set_bit(XPT_LISTENER, &cma_xprt->sc_xprt.xpt_flags);
@@ -913,6 +986,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
(size_t)svcrdma_max_requests);
newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests;
+ if (!svc_rdma_prealloc_ctxts(newxprt))
+ goto errout;
+
/*
* Limit ORD based on client limit, local device limit, and
* configured svcrdma limit.
@@ -1174,15 +1250,15 @@ 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 */
rdma_dealloc_frmr_q(rdma);
+ svc_rdma_destroy_ctxts(rdma);
/* Destroy the QP if present (not a listener) */
if (rdma->sc_qp && !IS_ERR(rdma->sc_qp))
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 04/10] svcrdma: Improve allocation of struct svc_rdma_req_map
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (2 preceding siblings ...)
2016-01-07 19:49 ` [PATCH v5 03/10] svcrdma: Improve allocation of struct svc_rdma_op_ctxt Chuck Lever
@ 2016-01-07 19:49 ` Chuck Lever
2016-01-07 19:49 ` [PATCH v5 05/10] svcrdma: Remove unused req_map and ctxt kmem_caches Chuck Lever
` (6 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:49 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
To ensure this allocation cannot fail and will not sleep,
pre-allocate the req_map structures per-connection.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 8 ++-
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 6 +-
net/sunrpc/xprtrdma/svc_rdma_transport.c | 85 ++++++++++++++++++++++++++----
3 files changed, 84 insertions(+), 15 deletions(-)
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index be2804b..05bf4fe 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -113,6 +113,7 @@ struct svc_rdma_fastreg_mr {
struct list_head frmr_list;
};
struct svc_rdma_req_map {
+ struct list_head free;
unsigned long count;
union {
struct kvec sge[RPCSVC_MAXPAGES];
@@ -145,6 +146,8 @@ struct svcxprt_rdma {
spinlock_t sc_ctxt_lock;
struct list_head sc_ctxts;
int sc_ctxt_used;
+ spinlock_t sc_map_lock;
+ struct list_head sc_maps;
struct list_head sc_rq_dto_q;
spinlock_t sc_rq_dto_lock;
@@ -223,8 +226,9 @@ extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt);
-extern struct svc_rdma_req_map *svc_rdma_get_req_map(void);
-extern void svc_rdma_put_req_map(struct svc_rdma_req_map *);
+extern struct svc_rdma_req_map *svc_rdma_get_req_map(struct svcxprt_rdma *);
+extern void svc_rdma_put_req_map(struct svcxprt_rdma *,
+ struct svc_rdma_req_map *);
extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *);
extern void svc_rdma_put_frmr(struct svcxprt_rdma *,
struct svc_rdma_fastreg_mr *);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 969a1ab..9a097f9 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -591,7 +591,7 @@ 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();
+ vec = svc_rdma_get_req_map(rdma);
ret = map_xdr(rdma, &rqstp->rq_res, vec);
if (ret)
goto err0;
@@ -630,14 +630,14 @@ 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 9801115..0b9e17e 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -273,23 +273,83 @@ static void svc_rdma_destroy_ctxts(struct svcxprt_rdma *xprt)
}
}
-/*
- * 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 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)
+{
+ 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 svc_rdma_req_map *map)
+void svc_rdma_put_req_map(struct svcxprt_rdma *xprt,
+ struct svc_rdma_req_map *map)
{
- kmem_cache_free(svc_rdma_map_cachep, map);
+ spin_lock(&xprt->sc_map_lock);
+ list_add(&map->free, &xprt->sc_maps);
+ spin_unlock(&xprt->sc_map_lock);
+}
+
+static void svc_rdma_destroy_maps(struct svcxprt_rdma *xprt)
+{
+ 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 */
@@ -593,12 +653,14 @@ static struct svcxprt_rdma *rdma_create_xprt(struct svc_serv *serv,
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);
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);
@@ -988,6 +1050,8 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
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
@@ -1259,6 +1323,7 @@ static void __svc_rdma_free(struct work_struct *work)
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))
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 05/10] svcrdma: Remove unused req_map and ctxt kmem_caches
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (3 preceding siblings ...)
2016-01-07 19:49 ` [PATCH v5 04/10] svcrdma: Improve allocation of struct svc_rdma_req_map Chuck Lever
@ 2016-01-07 19:49 ` Chuck Lever
2016-01-07 19:49 ` [PATCH v5 06/10] svcrdma: Add gfp flags to svc_rdma_post_recv() Chuck Lever
` (5 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:49 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
Clean up.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 1 +
net/sunrpc/xprtrdma/svc_rdma.c | 35 -----------------------------------
net/sunrpc/xprtrdma/xprt_rdma.h | 7 -------
3 files changed, 1 insertion(+), 42 deletions(-)
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 05bf4fe..141edbb 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -242,6 +242,7 @@ extern struct svc_xprt_class svc_rdma_bc_class;
#endif
/* svc_rdma.c */
+extern struct workqueue_struct *svc_rdma_wq;
extern int svc_rdma_init(void);
extern void svc_rdma_cleanup(void);
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index 1b7051b..e894e06 100644
--- a/net/sunrpc/xprtrdma/svc_rdma.c
+++ b/net/sunrpc/xprtrdma/svc_rdma.c
@@ -71,10 +71,6 @@ 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;
/*
@@ -243,8 +239,6 @@ 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)
@@ -264,39 +258,10 @@ 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/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 4197191..72276c7 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -528,11 +528,4 @@ 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;
-
#endif /* _LINUX_SUNRPC_XPRT_RDMA_H */
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 06/10] svcrdma: Add gfp flags to svc_rdma_post_recv()
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (4 preceding siblings ...)
2016-01-07 19:49 ` [PATCH v5 05/10] svcrdma: Remove unused req_map and ctxt kmem_caches Chuck Lever
@ 2016-01-07 19:49 ` Chuck Lever
2016-01-07 19:49 ` [PATCH v5 07/10] svcrdma: Remove last two __GFP_NOFAIL call sites Chuck Lever
` (4 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:49 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
svc_rdma_post_recv() allocates pages for receive buffers on-demand.
It uses GFP_KERNEL so the allocator tries hard, and may sleep. But
I'm about to add a call to svc_rdma_post_recv() from a function
that may not sleep.
Since all svc_rdma_post_recv() call sites can tolerate its failure,
allow it to fail if the page allocator returns nothing. Longer term,
receive buffers, being a finite resource per-connection, should be
pre-allocated and re-used.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 2 +-
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 2 +-
net/sunrpc/xprtrdma/svc_rdma_transport.c | 8 +++++---
3 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 141edbb..729ff35 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -221,7 +221,7 @@ extern struct rpcrdma_read_chunk *
extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *);
extern void svc_rdma_send_error(struct svcxprt_rdma *, struct rpcrdma_msg *,
enum rpcrdma_errcode);
-extern int svc_rdma_post_recv(struct svcxprt_rdma *);
+extern int svc_rdma_post_recv(struct svcxprt_rdma *, gfp_t);
extern int svc_rdma_create_listen(struct svc_serv *, int, struct sockaddr *);
extern struct svc_rdma_op_ctxt *svc_rdma_get_context(struct svcxprt_rdma *);
extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 9a097f9..aeaec7a 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -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."
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 0b9e17e..20fc095 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -668,7 +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;
@@ -686,7 +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,
@@ -1182,7 +1184,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
/* Post receive buffers */
for (i = 0; i < newxprt->sc_max_requests; i++) {
- ret = svc_rdma_post_recv(newxprt);
+ ret = svc_rdma_post_recv(newxprt, GFP_KERNEL);
if (ret) {
dprintk("svcrdma: failure posting receive buffers\n");
goto errout;
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 07/10] svcrdma: Remove last two __GFP_NOFAIL call sites
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (5 preceding siblings ...)
2016-01-07 19:49 ` [PATCH v5 06/10] svcrdma: Add gfp flags to svc_rdma_post_recv() Chuck Lever
@ 2016-01-07 19:49 ` Chuck Lever
2016-01-07 19:49 ` [PATCH v5 08/10] svcrdma: Make map_xdr non-static Chuck Lever
` (3 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:49 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
Clean up.
These functions can otherwise fail, so check for page allocation
failures too.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 5 ++++-
net/sunrpc/xprtrdma/svc_rdma_transport.c | 4 +++-
2 files changed, 7 insertions(+), 2 deletions(-)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index aeaec7a..de7df7b 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -598,7 +598,10 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
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)
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 20fc095..8b3ee04 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -1445,7 +1445,9 @@ 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 */
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 08/10] svcrdma: Make map_xdr non-static
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (6 preceding siblings ...)
2016-01-07 19:49 ` [PATCH v5 07/10] svcrdma: Remove last two __GFP_NOFAIL call sites Chuck Lever
@ 2016-01-07 19:49 ` Chuck Lever
2016-01-07 19:50 ` [PATCH v5 09/10] svcrdma: Define maximum number of backchannel requests Chuck Lever
` (2 subsequent siblings)
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:49 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
Pre-requisite to use map_xdr in the backchannel code.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 2 ++
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 14 +++++++-------
2 files changed, 9 insertions(+), 7 deletions(-)
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 729ff35..aeffa30 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -213,6 +213,8 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
u32, u32, u64, bool);
/* svc_rdma_sendto.c */
+extern int svc_rdma_map_xdr(struct svcxprt_rdma *, struct xdr_buf *,
+ struct svc_rdma_req_map *);
extern int svc_rdma_sendto(struct svc_rqst *);
extern struct rpcrdma_read_chunk *
svc_rdma_get_read_chunk(struct rpcrdma_msg *);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index de7df7b..3c25052 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;
@@ -592,7 +592,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
ctxt = svc_rdma_get_context(rdma);
ctxt->direction = DMA_TO_DEVICE;
vec = svc_rdma_get_req_map(rdma);
- ret = map_xdr(rdma, &rqstp->rq_res, vec);
+ ret = svc_rdma_map_xdr(rdma, &rqstp->rq_res, vec);
if (ret)
goto err0;
inline_bytes = rqstp->rq_res.len;
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 09/10] svcrdma: Define maximum number of backchannel requests
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (7 preceding siblings ...)
2016-01-07 19:49 ` [PATCH v5 08/10] svcrdma: Make map_xdr non-static Chuck Lever
@ 2016-01-07 19:50 ` Chuck Lever
2016-01-07 19:50 ` [PATCH v5 10/10] svcrdma: Add class for RDMA backwards direction transport Chuck Lever
2016-01-08 7:53 ` [PATCH v5 11/10] svc_rdma: use local_dma_lkey Christoph Hellwig
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:50 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
Extra resources for handling backchannel requests have to be
pre-allocated when a transport instance is created. Set up
additional fields in svcxprt_rdma to track these resources.
The max_requests fields are elements of the RPC-over-RDMA
protocol, so they should be u32. To ensure that unsigned
arithmetic is used everywhere, some other fields in the
svcxprt_rdma struct are updated.
Signed-off-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 13 ++++++++++---
net/sunrpc/xprtrdma/svc_rdma.c | 6 ++++--
net/sunrpc/xprtrdma/svc_rdma_transport.c | 24 ++++++++++++++----------
3 files changed, 28 insertions(+), 15 deletions(-)
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index aeffa30..9a2c418 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -51,6 +51,7 @@
/* RPC/RDMA parameters and stats */
extern unsigned int svcrdma_ord;
extern unsigned int svcrdma_max_requests;
+extern unsigned int svcrdma_max_bc_requests;
extern unsigned int svcrdma_max_req_size;
extern atomic_t rdma_stat_recv;
@@ -134,10 +135,11 @@ struct svcxprt_rdma {
int sc_max_sge;
int sc_max_sge_rd; /* max sge for read target */
- int sc_sq_depth; /* Depth of SQ */
atomic_t sc_sq_count; /* Number of SQ WR on queue */
-
- int sc_max_requests; /* Depth of RQ */
+ unsigned int sc_sq_depth; /* Depth of SQ */
+ unsigned int sc_rq_depth; /* Depth of RQ */
+ u32 sc_max_requests; /* Forward credits */
+ u32 sc_max_bc_requests;/* Backward credits */
int sc_max_req_size; /* Size of each RQ WR buf */
struct ib_pd *sc_pd;
@@ -186,6 +188,11 @@ struct svcxprt_rdma {
#define RPCRDMA_MAX_REQUESTS 32
#define RPCRDMA_MAX_REQ_SIZE 4096
+/* Typical ULP usage of BC requests is NFSv4.1 backchannel. Our
+ * current NFSv4.1 implementation supports one backchannel slot.
+ */
+#define RPCRDMA_MAX_BC_REQUESTS 2
+
#define RPCSVC_MAXPAYLOAD_RDMA RPCSVC_MAXPAYLOAD
/* svc_rdma_marshal.c */
diff --git a/net/sunrpc/xprtrdma/svc_rdma.c b/net/sunrpc/xprtrdma/svc_rdma.c
index e894e06..c846ca9 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;
@@ -245,9 +246,10 @@ 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);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 8b3ee04..af86dfe 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -169,12 +169,12 @@ static struct svc_rdma_op_ctxt *alloc_ctxt(struct svcxprt_rdma *xprt,
static bool svc_rdma_prealloc_ctxts(struct svcxprt_rdma *xprt)
{
- int i;
+ 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_max_requests;
+ i = xprt->sc_sq_depth + xprt->sc_rq_depth;
while (i--) {
struct svc_rdma_op_ctxt *ctxt;
@@ -285,7 +285,7 @@ static struct svc_rdma_req_map *alloc_req_map(gfp_t flags)
static bool svc_rdma_prealloc_maps(struct svcxprt_rdma *xprt)
{
- int i;
+ unsigned int i;
/* One for each receive buffer on this connection. */
i = xprt->sc_max_requests;
@@ -1016,8 +1016,8 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
struct ib_device *dev;
int uninitialized_var(dma_mr_acc);
int need_dma_mr = 0;
+ unsigned int i;
int ret = 0;
- int i;
listen_rdma = container_of(xprt, struct svcxprt_rdma, sc_xprt);
clear_bit(XPT_CONN, &xprt->xpt_flags);
@@ -1046,9 +1046,13 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
newxprt->sc_max_sge_rd = min_t(size_t, dev->attrs.max_sge_rd,
RPCSVC_MAXPAGES);
newxprt->sc_max_req_size = svcrdma_max_req_size;
- newxprt->sc_max_requests = min((size_t)dev->attrs.max_qp_wr,
- (size_t)svcrdma_max_requests);
- newxprt->sc_sq_depth = RPCRDMA_SQ_DEPTH_MULT * newxprt->sc_max_requests;
+ 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;
@@ -1077,7 +1081,7 @@ 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;
+ cq_attr.cqe = newxprt->sc_rq_depth;
newxprt->sc_rq_cq = ib_create_cq(dev,
rq_comp_handler,
cq_event_handler,
@@ -1092,7 +1096,7 @@ 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;
@@ -1183,7 +1187,7 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
newxprt->sc_dma_lkey = dev->local_dma_lkey;
/* Post receive buffers */
- for (i = 0; i < newxprt->sc_max_requests; i++) {
+ 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");
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 10/10] svcrdma: Add class for RDMA backwards direction transport
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (8 preceding siblings ...)
2016-01-07 19:50 ` [PATCH v5 09/10] svcrdma: Define maximum number of backchannel requests Chuck Lever
@ 2016-01-07 19:50 ` Chuck Lever
2016-01-08 7:53 ` [PATCH v5 11/10] svc_rdma: use local_dma_lkey Christoph Hellwig
10 siblings, 0 replies; 14+ messages in thread
From: Chuck Lever @ 2016-01-07 19:50 UTC (permalink / raw)
To: bfields-uC3wQj2KruNg9hUCZPvPmw, dledford-H+wXaHxf7aLQT0dZR+AlfA
Cc: linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
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-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Acked-by: Bruce Fields <bfields-uC3wQj2KruNg9hUCZPvPmw@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 5
net/sunrpc/xprt.c | 1
net/sunrpc/xprtrdma/Makefile | 2
net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 371 ++++++++++++++++++++++++++++
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 52 ++++
net/sunrpc/xprtrdma/svc_rdma_transport.c | 14 +
net/sunrpc/xprtrdma/transport.c | 30 +-
net/sunrpc/xprtrdma/xprt_rdma.h | 15 +
8 files changed, 475 insertions(+), 15 deletions(-)
create mode 100644 net/sunrpc/xprtrdma/svc_rdma_backchannel.c
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index 9a2c418..b13513a 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -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 *,
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 2e98f4a..37edea6 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 33f99d3..dc9f3b5 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/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
new file mode 100644
index 0000000..deff06a
--- /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_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 ff4f01e..3dfe464 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -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_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index af86dfe..7fd2395 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -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);
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 8c545f7..5c7d235 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;
@@ -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");
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 72276c7..5a38236 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
*/
@@ -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 */
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH v5 11/10] svc_rdma: use local_dma_lkey
[not found] ` <20160107194251.2662.88158.stgit-Hs+gFlyCn65vLzlybtyyYzGyq/o6K9yX@public.gmane.org>
` (9 preceding siblings ...)
2016-01-07 19:50 ` [PATCH v5 10/10] svcrdma: Add class for RDMA backwards direction transport Chuck Lever
@ 2016-01-08 7:53 ` Christoph Hellwig
[not found] ` <20160108075341.GA24754-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>
10 siblings, 1 reply; 14+ messages in thread
From: Christoph Hellwig @ 2016-01-08 7:53 UTC (permalink / raw)
To: Chuck Lever, bfields-uC3wQj2KruNg9hUCZPvPmw
Cc: dledford-H+wXaHxf7aLQT0dZR+AlfA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA,
linux-nfs-u79uwXL29TY76Z2rM5mHXA
We now alwasy have a per-PD local_dma_lkey available. Make use of that
fact in svc_rdma and stop registering our own MR.
Signed-off-by: Christoph Hellwig <hch-jcswGhMUV9g@public.gmane.org>
Reviewed-by: Sagi Grimberg <sagig-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Reviewed-by: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Reviewed-by: Chuck Lever <chuck.lever-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Reviewed-by: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
---
include/linux/sunrpc/svc_rdma.h | 2 --
net/sunrpc/xprtrdma/svc_rdma_backchannel.c | 2 +-
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c | 4 ++--
net/sunrpc/xprtrdma/svc_rdma_sendto.c | 6 ++---
net/sunrpc/xprtrdma/svc_rdma_transport.c | 36 ++++--------------------------
5 files changed, 10 insertions(+), 40 deletions(-)
diff --git a/include/linux/sunrpc/svc_rdma.h b/include/linux/sunrpc/svc_rdma.h
index b13513a..5322fea 100644
--- a/include/linux/sunrpc/svc_rdma.h
+++ b/include/linux/sunrpc/svc_rdma.h
@@ -156,13 +156,11 @@ struct svcxprt_rdma {
struct ib_qp *sc_qp;
struct ib_cq *sc_rq_cq;
struct ib_cq *sc_sq_cq;
- struct ib_mr *sc_phys_mr; /* MR for server memory */
int (*sc_reader)(struct svcxprt_rdma *,
struct svc_rqst *,
struct svc_rdma_op_ctxt *,
int *, u32 *, u32, u32, u64, bool);
u32 sc_dev_caps; /* distilled device caps */
- u32 sc_dma_lkey; /* local dma key */
unsigned int sc_frmr_pg_list_len;
struct list_head sc_frmr_q;
spinlock_t sc_frmr_q_lock;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index deff06a..65a7c23 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -128,7 +128,7 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
ctxt->wr_op = IB_WR_SEND;
ctxt->direction = DMA_TO_DEVICE;
- ctxt->sge[0].lkey = rdma->sc_dma_lkey;
+ 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,
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index 3dfe464..c8b8a8b 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++;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 3c25052..df57f3c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -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++;
@@ -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) {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 7fd2395..5763825 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -232,11 +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,
@@ -698,7 +698,7 @@ int svc_rdma_post_recv(struct svcxprt_rdma *xprt, gfp_t flags)
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;
}
@@ -1014,8 +1014,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
struct ib_cq_init_attr cq_attr = {};
struct ib_qp_init_attr qp_attr;
struct ib_device *dev;
- int uninitialized_var(dma_mr_acc);
- int need_dma_mr = 0;
unsigned int i;
int ret = 0;
@@ -1160,32 +1158,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
!rdma_ib_or_roce(dev, newxprt->sc_cm_id->port_num))
goto errout;
- if (!(newxprt->sc_dev_caps & SVCRDMA_DEVCAP_FAST_REG) ||
- !(dev->attrs.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)) {
- need_dma_mr = 1;
- dma_mr_acc = IB_ACCESS_LOCAL_WRITE;
- if (rdma_protocol_iwarp(dev, 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(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 = dev->local_dma_lkey;
-
/* Post receive buffers */
for (i = 0; i < newxprt->sc_rq_depth; i++) {
ret = svc_rdma_post_recv(newxprt, GFP_KERNEL);
@@ -1349,9 +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);
@@ -1479,7 +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 */
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related [flat|nested] 14+ messages in thread