summaryrefslogtreecommitdiffstats
path: root/net/sunrpc/xprtrdma
diff options
context:
space:
mode:
Diffstat (limited to 'net/sunrpc/xprtrdma')
-rw-r--r--net/sunrpc/xprtrdma/rpc_rdma.c86
-rw-r--r--net/sunrpc/xprtrdma/verbs.c53
-rw-r--r--net/sunrpc/xprtrdma/xprt_rdma.h1
3 files changed, 88 insertions, 52 deletions
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 2ac3f6e8adff..554d0814c875 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -87,6 +87,8 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
enum rpcrdma_chunktype type, struct rpcrdma_mr_seg *seg, int nsegs)
{
int len, n = 0, p;
+ int page_base;
+ struct page **ppages;
if (pos == 0 && xdrbuf->head[0].iov_len) {
seg[n].mr_page = NULL;
@@ -95,34 +97,32 @@ rpcrdma_convert_iovs(struct xdr_buf *xdrbuf, unsigned int pos,
++n;
}
- if (xdrbuf->page_len && (xdrbuf->pages[0] != NULL)) {
- if (n == nsegs)
- return 0;
- seg[n].mr_page = xdrbuf->pages[0];
- seg[n].mr_offset = (void *)(unsigned long) xdrbuf->page_base;
- seg[n].mr_len = min_t(u32,
- PAGE_SIZE - xdrbuf->page_base, xdrbuf->page_len);
- len = xdrbuf->page_len - seg[n].mr_len;
+ len = xdrbuf->page_len;
+ ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT);
+ page_base = xdrbuf->page_base & ~PAGE_MASK;
+ p = 0;
+ while (len && n < nsegs) {
+ seg[n].mr_page = ppages[p];
+ seg[n].mr_offset = (void *)(unsigned long) page_base;
+ seg[n].mr_len = min_t(u32, PAGE_SIZE - page_base, len);
+ BUG_ON(seg[n].mr_len > PAGE_SIZE);
+ len -= seg[n].mr_len;
++n;
- p = 1;
- while (len > 0) {
- if (n == nsegs)
- return 0;
- seg[n].mr_page = xdrbuf->pages[p];
- seg[n].mr_offset = NULL;
- seg[n].mr_len = min_t(u32, PAGE_SIZE, len);
- len -= seg[n].mr_len;
- ++n;
- ++p;
- }
+ ++p;
+ page_base = 0; /* page offset only applies to first page */
}
+ /* Message overflows the seg array */
+ if (len && n == nsegs)
+ return 0;
+
if (xdrbuf->tail[0].iov_len) {
/* the rpcrdma protocol allows us to omit any trailing
* xdr pad bytes, saving the server an RDMA operation. */
if (xdrbuf->tail[0].iov_len < 4 && xprt_rdma_pad_optimize)
return n;
if (n == nsegs)
+ /* Tail remains, but we're out of segments */
return 0;
seg[n].mr_page = NULL;
seg[n].mr_offset = xdrbuf->tail[0].iov_base;
@@ -296,6 +296,8 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad)
int copy_len;
unsigned char *srcp, *destp;
struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
+ int page_base;
+ struct page **ppages;
destp = rqst->rq_svec[0].iov_base;
curlen = rqst->rq_svec[0].iov_len;
@@ -324,28 +326,25 @@ rpcrdma_inline_pullup(struct rpc_rqst *rqst, int pad)
__func__, destp + copy_len, curlen);
rqst->rq_svec[0].iov_len += curlen;
}
-
r_xprt->rx_stats.pullup_copy_count += copy_len;
- npages = PAGE_ALIGN(rqst->rq_snd_buf.page_base+copy_len) >> PAGE_SHIFT;
+
+ page_base = rqst->rq_snd_buf.page_base;
+ ppages = rqst->rq_snd_buf.pages + (page_base >> PAGE_SHIFT);
+ page_base &= ~PAGE_MASK;
+ npages = PAGE_ALIGN(page_base+copy_len) >> PAGE_SHIFT;
for (i = 0; copy_len && i < npages; i++) {
- if (i == 0)
- curlen = PAGE_SIZE - rqst->rq_snd_buf.page_base;
- else
- curlen = PAGE_SIZE;
+ curlen = PAGE_SIZE - page_base;
if (curlen > copy_len)
curlen = copy_len;
dprintk("RPC: %s: page %d destp 0x%p len %d curlen %d\n",
__func__, i, destp, copy_len, curlen);
- srcp = kmap_atomic(rqst->rq_snd_buf.pages[i],
- KM_SKB_SUNRPC_DATA);
- if (i == 0)
- memcpy(destp, srcp+rqst->rq_snd_buf.page_base, curlen);
- else
- memcpy(destp, srcp, curlen);
+ srcp = kmap_atomic(ppages[i], KM_SKB_SUNRPC_DATA);
+ memcpy(destp, srcp+page_base, curlen);
kunmap_atomic(srcp, KM_SKB_SUNRPC_DATA);
rqst->rq_svec[0].iov_len += curlen;
destp += curlen;
copy_len -= curlen;
+ page_base = 0;
}
/* header now contains entire send message */
return pad;
@@ -606,6 +605,8 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
{
int i, npages, curlen, olen;
char *destp;
+ struct page **ppages;
+ int page_base;
curlen = rqst->rq_rcv_buf.head[0].iov_len;
if (curlen > copy_len) { /* write chunk header fixup */
@@ -624,32 +625,29 @@ rpcrdma_inline_fixup(struct rpc_rqst *rqst, char *srcp, int copy_len, int pad)
olen = copy_len;
i = 0;
rpcx_to_rdmax(rqst->rq_xprt)->rx_stats.fixup_copy_count += olen;
+ page_base = rqst->rq_rcv_buf.page_base;
+ ppages = rqst->rq_rcv_buf.pages + (page_base >> PAGE_SHIFT);
+ page_base &= ~PAGE_MASK;
+
if (copy_len && rqst->rq_rcv_buf.page_len) {
- npages = PAGE_ALIGN(rqst->rq_rcv_buf.page_base +
+ npages = PAGE_ALIGN(page_base +
rqst->rq_rcv_buf.page_len) >> PAGE_SHIFT;
for (; i < npages; i++) {
- if (i == 0)
- curlen = PAGE_SIZE - rqst->rq_rcv_buf.page_base;
- else
- curlen = PAGE_SIZE;
+ curlen = PAGE_SIZE - page_base;
if (curlen > copy_len)
curlen = copy_len;
dprintk("RPC: %s: page %d"
" srcp 0x%p len %d curlen %d\n",
__func__, i, srcp, copy_len, curlen);
- destp = kmap_atomic(rqst->rq_rcv_buf.pages[i],
- KM_SKB_SUNRPC_DATA);
- if (i == 0)
- memcpy(destp + rqst->rq_rcv_buf.page_base,
- srcp, curlen);
- else
- memcpy(destp, srcp, curlen);
- flush_dcache_page(rqst->rq_rcv_buf.pages[i]);
+ destp = kmap_atomic(ppages[i], KM_SKB_SUNRPC_DATA);
+ memcpy(destp + page_base, srcp, curlen);
+ flush_dcache_page(ppages[i]);
kunmap_atomic(destp, KM_SKB_SUNRPC_DATA);
srcp += curlen;
copy_len -= curlen;
if (copy_len == 0)
break;
+ page_base = 0;
}
rqst->rq_rcv_buf.page_len = olen - copy_len;
} else
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 5f4c7b3bc711..d4297dc43dc4 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -144,6 +144,7 @@ rpcrdma_cq_async_error_upcall(struct ib_event *event, void *context)
static inline
void rpcrdma_event_process(struct ib_wc *wc)
{
+ struct rpcrdma_mw *frmr;
struct rpcrdma_rep *rep =
(struct rpcrdma_rep *)(unsigned long) wc->wr_id;
@@ -154,15 +155,23 @@ void rpcrdma_event_process(struct ib_wc *wc)
return;
if (IB_WC_SUCCESS != wc->status) {
- dprintk("RPC: %s: %s WC status %X, connection lost\n",
- __func__, (wc->opcode & IB_WC_RECV) ? "recv" : "send",
- wc->status);
+ dprintk("RPC: %s: WC opcode %d status %X, connection lost\n",
+ __func__, wc->opcode, wc->status);
rep->rr_len = ~0U;
- rpcrdma_schedule_tasklet(rep);
+ if (wc->opcode != IB_WC_FAST_REG_MR && wc->opcode != IB_WC_LOCAL_INV)
+ rpcrdma_schedule_tasklet(rep);
return;
}
switch (wc->opcode) {
+ case IB_WC_FAST_REG_MR:
+ frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+ frmr->r.frmr.state = FRMR_IS_VALID;
+ break;
+ case IB_WC_LOCAL_INV:
+ frmr = (struct rpcrdma_mw *)(unsigned long)wc->wr_id;
+ frmr->r.frmr.state = FRMR_IS_INVALID;
+ break;
case IB_WC_RECV:
rep->rr_len = wc->byte_len;
ib_dma_sync_single_for_cpu(
@@ -1450,6 +1459,12 @@ rpcrdma_map_one(struct rpcrdma_ia *ia, struct rpcrdma_mr_seg *seg, int writing)
seg->mr_dma = ib_dma_map_single(ia->ri_id->device,
seg->mr_offset,
seg->mr_dmalen, seg->mr_dir);
+ if (ib_dma_mapping_error(ia->ri_id->device, seg->mr_dma)) {
+ dprintk("RPC: %s: mr_dma %llx mr_offset %p mr_dma_len %zu\n",
+ __func__,
+ (unsigned long long)seg->mr_dma,
+ seg->mr_offset, seg->mr_dmalen);
+ }
}
static void
@@ -1469,7 +1484,8 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
struct rpcrdma_xprt *r_xprt)
{
struct rpcrdma_mr_seg *seg1 = seg;
- struct ib_send_wr frmr_wr, *bad_wr;
+ struct ib_send_wr invalidate_wr, frmr_wr, *bad_wr, *post_wr;
+
u8 key;
int len, pageoff;
int i, rc;
@@ -1484,6 +1500,7 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
rpcrdma_map_one(ia, seg, writing);
seg1->mr_chunk.rl_mw->r.frmr.fr_pgl->page_list[i] = seg->mr_dma;
len += seg->mr_len;
+ BUG_ON(seg->mr_len > PAGE_SIZE);
++seg;
++i;
/* Check for holes */
@@ -1494,26 +1511,45 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
dprintk("RPC: %s: Using frmr %p to map %d segments\n",
__func__, seg1->mr_chunk.rl_mw, i);
+ if (unlikely(seg1->mr_chunk.rl_mw->r.frmr.state == FRMR_IS_VALID)) {
+ dprintk("RPC: %s: frmr %x left valid, posting invalidate.\n",
+ __func__,
+ seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey);
+ /* Invalidate before using. */
+ memset(&invalidate_wr, 0, sizeof invalidate_wr);
+ invalidate_wr.wr_id = (unsigned long)(void *)seg1->mr_chunk.rl_mw;
+ invalidate_wr.next = &frmr_wr;
+ invalidate_wr.opcode = IB_WR_LOCAL_INV;
+ invalidate_wr.send_flags = IB_SEND_SIGNALED;
+ invalidate_wr.ex.invalidate_rkey =
+ seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey;
+ DECR_CQCOUNT(&r_xprt->rx_ep);
+ post_wr = &invalidate_wr;
+ } else
+ post_wr = &frmr_wr;
+
/* Bump the key */
key = (u8)(seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey & 0x000000FF);
ib_update_fast_reg_key(seg1->mr_chunk.rl_mw->r.frmr.fr_mr, ++key);
/* Prepare FRMR WR */
memset(&frmr_wr, 0, sizeof frmr_wr);
+ frmr_wr.wr_id = (unsigned long)(void *)seg1->mr_chunk.rl_mw;
frmr_wr.opcode = IB_WR_FAST_REG_MR;
- frmr_wr.send_flags = 0; /* unsignaled */
+ frmr_wr.send_flags = IB_SEND_SIGNALED;
frmr_wr.wr.fast_reg.iova_start = seg1->mr_dma;
frmr_wr.wr.fast_reg.page_list = seg1->mr_chunk.rl_mw->r.frmr.fr_pgl;
frmr_wr.wr.fast_reg.page_list_len = i;
frmr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
frmr_wr.wr.fast_reg.length = i << PAGE_SHIFT;
+ BUG_ON(frmr_wr.wr.fast_reg.length < len);
frmr_wr.wr.fast_reg.access_flags = (writing ?
IB_ACCESS_REMOTE_WRITE | IB_ACCESS_LOCAL_WRITE :
IB_ACCESS_REMOTE_READ);
frmr_wr.wr.fast_reg.rkey = seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey;
DECR_CQCOUNT(&r_xprt->rx_ep);
- rc = ib_post_send(ia->ri_id->qp, &frmr_wr, &bad_wr);
+ rc = ib_post_send(ia->ri_id->qp, post_wr, &bad_wr);
if (rc) {
dprintk("RPC: %s: failed ib_post_send for register,"
@@ -1542,8 +1578,9 @@ rpcrdma_deregister_frmr_external(struct rpcrdma_mr_seg *seg,
rpcrdma_unmap_one(ia, seg++);
memset(&invalidate_wr, 0, sizeof invalidate_wr);
+ invalidate_wr.wr_id = (unsigned long)(void *)seg1->mr_chunk.rl_mw;
invalidate_wr.opcode = IB_WR_LOCAL_INV;
- invalidate_wr.send_flags = 0; /* unsignaled */
+ invalidate_wr.send_flags = IB_SEND_SIGNALED;
invalidate_wr.ex.invalidate_rkey = seg1->mr_chunk.rl_mw->r.frmr.fr_mr->rkey;
DECR_CQCOUNT(&r_xprt->rx_ep);
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index c7a7eba991bc..cae761a8536c 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -164,6 +164,7 @@ struct rpcrdma_mr_seg { /* chunk descriptors */
struct {
struct ib_fast_reg_page_list *fr_pgl;
struct ib_mr *fr_mr;
+ enum { FRMR_IS_INVALID, FRMR_IS_VALID } state;
} frmr;
} r;
struct list_head mw_list;
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-13 08:06:47 +0100