* [PATCH 2/2] RDMA: Remove defunct memory window and FMR registrations
2011-11-03 18:52 [PATCH 1/2] RDMA: RPCRDMA_MAX_DATA_SEGS cause i686 stack to blow Steve Dickson
@ 2011-11-03 18:52 ` Steve Dickson
2011-11-03 19:16 ` [PATCH 1/2] RDMA: RPCRDMA_MAX_DATA_SEGS cause i686 stack to blow Boaz Harrosh
2011-11-04 8:03 ` Max Matveev
2 siblings, 0 replies; 4+ messages in thread
From: Steve Dickson @ 2011-11-03 18:52 UTC (permalink / raw)
To: Linux NFS Mailing list
The patch removes support for memory window and FMR registrations
which in turn makes the code a bit easier to read.
Signed-off-by: Steve Dickson <steved@redhat.com>
---
include/linux/sunrpc/xprtrdma.h | 6 +-
net/sunrpc/xprtrdma/rpc_rdma.c | 33 +-----
net/sunrpc/xprtrdma/transport.c | 5 -
net/sunrpc/xprtrdma/verbs.c | 273 +--------------------------------------
net/sunrpc/xprtrdma/xprt_rdma.h | 5 +-
5 files changed, 7 insertions(+), 315 deletions(-)
diff --git a/include/linux/sunrpc/xprtrdma.h b/include/linux/sunrpc/xprtrdma.h
index c2f04e1..196992b 100644
--- a/include/linux/sunrpc/xprtrdma.h
+++ b/include/linux/sunrpc/xprtrdma.h
@@ -67,9 +67,9 @@
enum rpcrdma_memreg {
RPCRDMA_BOUNCEBUFFERS = 0,
RPCRDMA_REGISTER,
- RPCRDMA_MEMWINDOWS,
- RPCRDMA_MEMWINDOWS_ASYNC,
- RPCRDMA_MTHCAFMR,
+ RPCRDMA_XXX1, /* defunct - was MEMWINDOWS */
+ RPCRDMA_XXX2, /* defunct - was MEMWINDOWS_ASYNC */
+ RPCRDMA_XXX3, /* defunct - was MTHCAFMR */
RPCRDMA_FRMR,
RPCRDMA_ALLPHYSICAL,
RPCRDMA_LAST
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 554d081..caeacf9 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -707,16 +707,6 @@ rpcrdma_conn_func(struct rpcrdma_ep *ep)
}
/*
- * This function is called when memory window unbind which we are waiting
- * for completes. Just use rr_func (zeroed by upcall) to signal completion.
- */
-static void
-rpcrdma_unbind_func(struct rpcrdma_rep *rep)
-{
- wake_up(&rep->rr_unbind);
-}
-
-/*
* Called as a tasklet to do req/reply match and complete a request
* Errors must result in the RPC task either being awakened, or
* allowed to timeout, to discover the errors at that time.
@@ -730,7 +720,7 @@ rpcrdma_reply_handler(struct rpcrdma_rep *rep)
struct rpc_xprt *xprt = rep->rr_xprt;
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
__be32 *iptr;
- int i, rdmalen, status;
+ int rdmalen, status;
/* Check status. If bad, signal disconnect and return rep to pool */
if (rep->rr_len == ~0U) {
@@ -854,27 +844,6 @@ badheader:
break;
}
- /* If using mw bind, start the deregister process now. */
- /* (Note: if mr_free(), cannot perform it here, in tasklet context) */
- if (req->rl_nchunks) switch (r_xprt->rx_ia.ri_memreg_strategy) {
- case RPCRDMA_MEMWINDOWS:
- for (i = 0; req->rl_nchunks-- > 1;)
- i += rpcrdma_deregister_external(
- &req->rl_segments[i], r_xprt, NULL);
- /* Optionally wait (not here) for unbinds to complete */
- rep->rr_func = rpcrdma_unbind_func;
- (void) rpcrdma_deregister_external(&req->rl_segments[i],
- r_xprt, rep);
- break;
- case RPCRDMA_MEMWINDOWS_ASYNC:
- for (i = 0; req->rl_nchunks--;)
- i += rpcrdma_deregister_external(&req->rl_segments[i],
- r_xprt, NULL);
- break;
- default:
- break;
- }
-
dprintk("RPC: %s: xprt_complete_rqst(0x%p, 0x%p, %d)\n",
__func__, xprt, rqst, status);
xprt_complete_rqst(rqst->rq_task, status);
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index b446e10..4188f24 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -598,11 +598,6 @@ xprt_rdma_free(void *buffer)
&req->rl_segments[i], r_xprt, NULL);
}
- if (rep && wait_event_interruptible(rep->rr_unbind, !rep->rr_func)) {
- rep->rr_func = NULL; /* abandon the callback */
- req->rl_reply = NULL;
- }
-
if (req->rl_iov.length == 0) { /* see allocate above */
struct rpcrdma_req *oreq = (struct rpcrdma_req *)req->rl_buffer;
oreq->rl_reply = req->rl_reply;
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 68ba0fb..e1e0079 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -494,33 +494,6 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
}
switch (memreg) {
- case RPCRDMA_MEMWINDOWS:
- case RPCRDMA_MEMWINDOWS_ASYNC:
- if (!(devattr.device_cap_flags & IB_DEVICE_MEM_WINDOW)) {
- dprintk("RPC: %s: MEMWINDOWS registration "
- "specified but not supported by adapter, "
- "using slower RPCRDMA_REGISTER\n",
- __func__);
- memreg = RPCRDMA_REGISTER;
- }
- break;
- case RPCRDMA_MTHCAFMR:
- if (!ia->ri_id->device->alloc_fmr) {
-#if RPCRDMA_PERSISTENT_REGISTRATION
- dprintk("RPC: %s: MTHCAFMR registration "
- "specified but not supported by adapter, "
- "using riskier RPCRDMA_ALLPHYSICAL\n",
- __func__);
- memreg = RPCRDMA_ALLPHYSICAL;
-#else
- dprintk("RPC: %s: MTHCAFMR registration "
- "specified but not supported by adapter, "
- "using slower RPCRDMA_REGISTER\n",
- __func__);
- memreg = RPCRDMA_REGISTER;
-#endif
- }
- break;
case RPCRDMA_FRMR:
/* Requires both frmr reg and local dma lkey */
if ((devattr.device_cap_flags &
@@ -561,18 +534,7 @@ rpcrdma_ia_open(struct rpcrdma_xprt *xprt, struct sockaddr *addr, int memreg)
mem_priv = IB_ACCESS_LOCAL_WRITE |
IB_ACCESS_REMOTE_WRITE |
IB_ACCESS_REMOTE_READ;
- goto register_setup;
#endif
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- mem_priv = IB_ACCESS_LOCAL_WRITE |
- IB_ACCESS_MW_BIND;
- goto register_setup;
- case RPCRDMA_MTHCAFMR:
- if (ia->ri_have_dma_lkey)
- break;
- mem_priv = IB_ACCESS_LOCAL_WRITE;
- register_setup:
ia->ri_bind_mem = ib_get_dma_mr(ia->ri_pd, mem_priv);
if (IS_ERR(ia->ri_bind_mem)) {
printk(KERN_ALERT "%s: ib_get_dma_mr for "
@@ -677,14 +639,6 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
ep->rep_attr.cap.max_send_wr = cdata->max_requests * 7;
}
break;
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- /* Add room for mw_binds+unbinds - overkill! */
- ep->rep_attr.cap.max_send_wr++;
- ep->rep_attr.cap.max_send_wr *= (2 * RPCRDMA_MAX_SEGS);
- if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
- return -EINVAL;
- break;
default:
break;
}
@@ -706,14 +660,6 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
/* set trigger for requesting send completion */
ep->rep_cqinit = ep->rep_attr.cap.max_send_wr/2 /* - 1*/;
- switch (ia->ri_memreg_strategy) {
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- ep->rep_cqinit -= RPCRDMA_MAX_SEGS;
- break;
- default:
- break;
- }
if (ep->rep_cqinit <= 2)
ep->rep_cqinit = 0;
INIT_CQCOUNT(ep);
@@ -980,7 +926,7 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
* 2. arrays of struct rpcrdma_req to fill in pointers
* 3. array of struct rpcrdma_rep for replies
* 4. padding, if any
- * 5. mw's, fmr's or frmr's, if any
+ * 5. frmr's, if any
* Send/recv buffers in req/rep need to be registered
*/
@@ -992,16 +938,6 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
len += buf->rb_max_requests * RPCRDMA_MAX_SEGS *
sizeof(struct rpcrdma_mw);
break;
- case RPCRDMA_MTHCAFMR:
- /* TBD we are perhaps overallocating here */
- len += (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS *
- sizeof(struct rpcrdma_mw);
- break;
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- len += (buf->rb_max_requests + 1) * RPCRDMA_MAX_SEGS *
- sizeof(struct rpcrdma_mw);
- break;
default:
break;
}
@@ -1033,7 +969,7 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
p += cdata->padding;
/*
- * Allocate the fmr's, or mw's for mw_bind chunk registration.
+ * Allocate any frmr's for mw_bind chunk registration.
* We "cycle" the mw's in order to minimize rkey reuse,
* and also reduce unbind-to-bind collision.
*/
@@ -1064,39 +1000,6 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
++r;
}
break;
- case RPCRDMA_MTHCAFMR:
- /* TBD we are perhaps overallocating here */
- for (i = (buf->rb_max_requests+1) * RPCRDMA_MAX_SEGS; i; i--) {
- static struct ib_fmr_attr fa =
- { RPCRDMA_MAX_DATA_SEGS, 1, PAGE_SHIFT };
- r->r.fmr = ib_alloc_fmr(ia->ri_pd,
- IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ,
- &fa);
- if (IS_ERR(r->r.fmr)) {
- rc = PTR_ERR(r->r.fmr);
- dprintk("RPC: %s: ib_alloc_fmr"
- " failed %i\n", __func__, rc);
- goto out;
- }
- list_add(&r->mw_list, &buf->rb_mws);
- ++r;
- }
- break;
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- /* Allocate one extra request's worth, for full cycling */
- for (i = (buf->rb_max_requests+1) * RPCRDMA_MAX_SEGS; i; i--) {
- r->r.mw = ib_alloc_mw(ia->ri_pd);
- if (IS_ERR(r->r.mw)) {
- rc = PTR_ERR(r->r.mw);
- dprintk("RPC: %s: ib_alloc_mw"
- " failed %i\n", __func__, rc);
- goto out;
- }
- list_add(&r->mw_list, &buf->rb_mws);
- ++r;
- }
- break;
default:
break;
}
@@ -1145,7 +1048,6 @@ rpcrdma_buffer_create(struct rpcrdma_buffer *buf, struct rpcrdma_ep *ep,
memset(rep, 0, sizeof(struct rpcrdma_rep));
buf->rb_recv_bufs[i] = rep;
buf->rb_recv_bufs[i]->rr_buffer = buf;
- init_waitqueue_head(&rep->rr_unbind);
rc = rpcrdma_register_internal(ia, rep->rr_base,
len - offsetof(struct rpcrdma_rep, rr_base),
@@ -1208,23 +1110,6 @@ rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
__func__, rc);
ib_free_fast_reg_page_list(r->r.frmr.fr_pgl);
break;
- case RPCRDMA_MTHCAFMR:
- rc = ib_dealloc_fmr(r->r.fmr);
- if (rc)
- dprintk("RPC: %s:"
- " ib_dealloc_fmr"
- " failed %i\n",
- __func__, rc);
- break;
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- rc = ib_dealloc_mw(r->r.mw);
- if (rc)
- dprintk("RPC: %s:"
- " ib_dealloc_mw"
- " failed %i\n",
- __func__, rc);
- break;
default:
break;
}
@@ -1305,15 +1190,11 @@ rpcrdma_buffer_put(struct rpcrdma_req *req)
req->rl_niovs = 0;
if (req->rl_reply) {
buffers->rb_recv_bufs[--buffers->rb_recv_index] = req->rl_reply;
- init_waitqueue_head(&req->rl_reply->rr_unbind);
req->rl_reply->rr_func = NULL;
req->rl_reply = NULL;
}
switch (ia->ri_memreg_strategy) {
case RPCRDMA_FRMR:
- case RPCRDMA_MTHCAFMR:
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
/*
* Cycle mw's back in reverse order, and "spin" them.
* This delays and scrambles reuse as much as possible.
@@ -1593,136 +1474,6 @@ rpcrdma_deregister_frmr_external(struct rpcrdma_mr_seg *seg,
}
static int
-rpcrdma_register_fmr_external(struct rpcrdma_mr_seg *seg,
- int *nsegs, int writing, struct rpcrdma_ia *ia)
-{
- struct rpcrdma_mr_seg *seg1 = seg;
- u64 physaddrs[RPCRDMA_MAX_DATA_SEGS];
- int len, pageoff, i, rc;
-
- pageoff = offset_in_page(seg1->mr_offset);
- seg1->mr_offset -= pageoff; /* start of page */
- seg1->mr_len += pageoff;
- len = -pageoff;
- if (*nsegs > RPCRDMA_MAX_DATA_SEGS)
- *nsegs = RPCRDMA_MAX_DATA_SEGS;
- for (i = 0; i < *nsegs;) {
- rpcrdma_map_one(ia, seg, writing);
- physaddrs[i] = seg->mr_dma;
- len += seg->mr_len;
- ++seg;
- ++i;
- /* Check for holes */
- if ((i < *nsegs && offset_in_page(seg->mr_offset)) ||
- offset_in_page((seg-1)->mr_offset + (seg-1)->mr_len))
- break;
- }
- rc = ib_map_phys_fmr(seg1->mr_chunk.rl_mw->r.fmr,
- physaddrs, i, seg1->mr_dma);
- if (rc) {
- dprintk("RPC: %s: failed ib_map_phys_fmr "
- "%u@0x%llx+%i (%d)... status %i\n", __func__,
- len, (unsigned long long)seg1->mr_dma,
- pageoff, i, rc);
- while (i--)
- rpcrdma_unmap_one(ia, --seg);
- } else {
- seg1->mr_rkey = seg1->mr_chunk.rl_mw->r.fmr->rkey;
- seg1->mr_base = seg1->mr_dma + pageoff;
- seg1->mr_nsegs = i;
- seg1->mr_len = len;
- }
- *nsegs = i;
- return rc;
-}
-
-static int
-rpcrdma_deregister_fmr_external(struct rpcrdma_mr_seg *seg,
- struct rpcrdma_ia *ia)
-{
- struct rpcrdma_mr_seg *seg1 = seg;
- LIST_HEAD(l);
- int rc;
-
- list_add(&seg1->mr_chunk.rl_mw->r.fmr->list, &l);
- rc = ib_unmap_fmr(&l);
- while (seg1->mr_nsegs--)
- rpcrdma_unmap_one(ia, seg++);
- if (rc)
- dprintk("RPC: %s: failed ib_unmap_fmr,"
- " status %i\n", __func__, rc);
- return rc;
-}
-
-static int
-rpcrdma_register_memwin_external(struct rpcrdma_mr_seg *seg,
- int *nsegs, int writing, struct rpcrdma_ia *ia,
- struct rpcrdma_xprt *r_xprt)
-{
- int mem_priv = (writing ? IB_ACCESS_REMOTE_WRITE :
- IB_ACCESS_REMOTE_READ);
- struct ib_mw_bind param;
- int rc;
-
- *nsegs = 1;
- rpcrdma_map_one(ia, seg, writing);
- param.mr = ia->ri_bind_mem;
- param.wr_id = 0ULL; /* no send cookie */
- param.addr = seg->mr_dma;
- param.length = seg->mr_len;
- param.send_flags = 0;
- param.mw_access_flags = mem_priv;
-
- DECR_CQCOUNT(&r_xprt->rx_ep);
- rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, ¶m);
- if (rc) {
- dprintk("RPC: %s: failed ib_bind_mw "
- "%u@0x%llx status %i\n",
- __func__, seg->mr_len,
- (unsigned long long)seg->mr_dma, rc);
- rpcrdma_unmap_one(ia, seg);
- } else {
- seg->mr_rkey = seg->mr_chunk.rl_mw->r.mw->rkey;
- seg->mr_base = param.addr;
- seg->mr_nsegs = 1;
- }
- return rc;
-}
-
-static int
-rpcrdma_deregister_memwin_external(struct rpcrdma_mr_seg *seg,
- struct rpcrdma_ia *ia,
- struct rpcrdma_xprt *r_xprt, void **r)
-{
- struct ib_mw_bind param;
- LIST_HEAD(l);
- int rc;
-
- BUG_ON(seg->mr_nsegs != 1);
- param.mr = ia->ri_bind_mem;
- param.addr = 0ULL; /* unbind */
- param.length = 0;
- param.mw_access_flags = 0;
- if (*r) {
- param.wr_id = (u64) (unsigned long) *r;
- param.send_flags = IB_SEND_SIGNALED;
- INIT_CQCOUNT(&r_xprt->rx_ep);
- } else {
- param.wr_id = 0ULL;
- param.send_flags = 0;
- DECR_CQCOUNT(&r_xprt->rx_ep);
- }
- rc = ib_bind_mw(ia->ri_id->qp, seg->mr_chunk.rl_mw->r.mw, ¶m);
- rpcrdma_unmap_one(ia, seg);
- if (rc)
- dprintk("RPC: %s: failed ib_(un)bind_mw,"
- " status %i\n", __func__, rc);
- else
- *r = NULL; /* will upcall on completion */
- return rc;
-}
-
-static int
rpcrdma_register_default_external(struct rpcrdma_mr_seg *seg,
int *nsegs, int writing, struct rpcrdma_ia *ia)
{
@@ -1807,17 +1558,6 @@ rpcrdma_register_external(struct rpcrdma_mr_seg *seg,
rc = rpcrdma_register_frmr_external(seg, &nsegs, writing, ia, r_xprt);
break;
- /* Registration using fmr memory registration */
- case RPCRDMA_MTHCAFMR:
- rc = rpcrdma_register_fmr_external(seg, &nsegs, writing, ia);
- break;
-
- /* Registration using memory windows */
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- rc = rpcrdma_register_memwin_external(seg, &nsegs, writing, ia, r_xprt);
- break;
-
/* Default registration each time */
default:
rc = rpcrdma_register_default_external(seg, &nsegs, writing, ia);
@@ -1850,15 +1590,6 @@ rpcrdma_deregister_external(struct rpcrdma_mr_seg *seg,
rc = rpcrdma_deregister_frmr_external(seg, ia, r_xprt);
break;
- case RPCRDMA_MTHCAFMR:
- rc = rpcrdma_deregister_fmr_external(seg, ia);
- break;
-
- case RPCRDMA_MEMWINDOWS_ASYNC:
- case RPCRDMA_MEMWINDOWS:
- rc = rpcrdma_deregister_memwin_external(seg, ia, r_xprt, &r);
- break;
-
default:
rc = rpcrdma_deregister_default_external(seg, ia);
break;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 8d588f2..10285db 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -125,7 +125,6 @@ struct rpcrdma_rep {
struct rpc_xprt *rr_xprt; /* needed for request/reply matching */
void (*rr_func)(struct rpcrdma_rep *);/* called by tasklet in softint */
struct list_head rr_list; /* tasklet list */
- wait_queue_head_t rr_unbind; /* optional unbind wait */
struct ib_sge rr_iov; /* for posting */
struct ib_mr *rr_handle; /* handle for mem in rr_iov */
char rr_base[MAX_RPCRDMAHDR]; /* minimal inline receive buffer */
@@ -160,8 +159,6 @@ struct rpcrdma_mr_seg { /* chunk descriptors */
struct ib_mr *rl_mr; /* if registered directly */
struct rpcrdma_mw { /* if registered from region */
union {
- struct ib_mw *mw;
- struct ib_fmr *fmr;
struct {
struct ib_fast_reg_page_list *fr_pgl;
struct ib_mr *fr_mr;
@@ -210,7 +207,7 @@ struct rpcrdma_buffer {
atomic_t rb_credits; /* most recent server credits */
unsigned long rb_cwndscale; /* cached framework rpc_cwndscale */
int rb_max_requests;/* client max requests */
- struct list_head rb_mws; /* optional memory windows/fmrs/frmrs */
+ struct list_head rb_mws; /* optional frmrs */
int rb_send_index;
struct rpcrdma_req **rb_send_bufs;
int rb_recv_index;
--
1.7.1
^ permalink raw reply related [flat|nested] 4+ messages in thread