/* 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, false);
if (ret)
goto out_err;
ret = svc_rdma_repost_recv(rdma, GFP_NOIO);
if (ret)
goto out_err;
ctxt = svc_rdma_get_context(rdma);
ctxt->pages[0] = virt_to_page(rqst->rq_buffer);
ctxt->count = 1;
ctxt->direction = DMA_TO_DEVICE;
ctxt->sge[0].lkey = rdma->sc_pd->local_dma_lkey;
ctxt->sge[0].length = sndbuf->len;
ctxt->sge[0].addr =
ib_dma_map_page(rdma->sc_cm_id->device, ctxt->pages[0], 0,
sndbuf->len, DMA_TO_DEVICE);
if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr)) {
ret = -EIO;
goto out_unmap;
}
svc_rdma_count_mappings(rdma, ctxt);
memset(&send_wr, 0, sizeof(send_wr));
ctxt->cqe.done = svc_rdma_wc_send;
send_wr.wr_cqe = &ctxt->cqe;
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;
}
/* 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_send_reply_msg, but takes a struct
* 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 svc_rdma_send_ctxt *ctxt)
{
int ret;
ret = svc_rdma_map_reply_msg(rdma, ctxt, &rqst->rq_snd_buf, NULL);
if (ret < 0)
return -EIO;
/* Bump page refcnt so Send completion doesn't release
* the rq_buffer before all retransmits are complete.
*/
get_page(virt_to_page(rqst->rq_buffer));
ctxt->sc_send_wr.opcode = IB_WR_SEND;
return svc_rdma_send(rdma, &ctxt->sc_send_wr);
}
static void svc_rdma_send_error(struct svcxprt_rdma *xprt,
__be32 *rdma_argp, int status)
{
struct svc_rdma_send_ctxt *ctxt;
unsigned int length;
__be32 *p;
int ret;
ctxt = svc_rdma_send_ctxt_get(xprt);
if (!ctxt)
return;
p = ctxt->sc_xprt_buf;
*p++ = *rdma_argp;
*p++ = *(rdma_argp + 1);
*p++ = xprt->sc_fc_credits;
*p++ = rdma_error;
switch (status) {
case -EPROTONOSUPPORT:
*p++ = err_vers;
*p++ = rpcrdma_version;
*p++ = rpcrdma_version;
trace_svcrdma_err_vers(*rdma_argp);
break;
default:
*p++ = err_chunk;
trace_svcrdma_err_chunk(*rdma_argp);
}
length = (unsigned long)p - (unsigned long)ctxt->sc_xprt_buf;
svc_rdma_sync_reply_hdr(xprt, ctxt, length);
ctxt->sc_send_wr.opcode = IB_WR_SEND;
ret = svc_rdma_send(xprt, &ctxt->sc_send_wr);
if (ret)
svc_rdma_send_ctxt_put(xprt, ctxt);
}
static int send_reply(struct svcxprt_rdma *rdma,
struct svc_rqst *rqstp,
struct page *page,
struct rpcrdma_msg *rdma_resp,
struct svc_rdma_op_ctxt *ctxt,
struct svc_rdma_req_map *vec,
int byte_count)
{
struct ib_send_wr send_wr;
struct ib_send_wr inv_wr;
int sge_no;
int sge_bytes;
int page_no;
int ret;
/* Post a recv buffer to handle another request. */
ret = svc_rdma_post_recv(rdma);
if (ret) {
printk(KERN_INFO
"svcrdma: could not post a receive buffer, err=%d."
"Closing transport %p.\n", ret, rdma);
set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
svc_rdma_put_frmr(rdma, vec->frmr);
svc_rdma_put_context(ctxt, 0);
return -ENOTCONN;
}
/* Prepare the context */
ctxt->pages[0] = page;
ctxt->count = 1;
ctxt->frmr = vec->frmr;
if (vec->frmr)
set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
else
clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
/* Prepare the SGE for the RPCRDMA Header */
ctxt->sge[0].lkey = rdma->sc_dma_lkey;
ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
ctxt->sge[0].addr =
ib_dma_map_single(rdma->sc_cm_id->device, page_address(page),
ctxt->sge[0].length, DMA_TO_DEVICE);
if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr))
goto err;
atomic_inc(&rdma->sc_dma_used);
ctxt->direction = DMA_TO_DEVICE;
/* Determine how many of our SGE are to be transmitted */
for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
byte_count -= sge_bytes;
if (!vec->frmr) {
ctxt->sge[sge_no].addr =
ib_dma_map_single(rdma->sc_cm_id->device,
vec->sge[sge_no].iov_base,
sge_bytes, DMA_TO_DEVICE);
if (ib_dma_mapping_error(rdma->sc_cm_id->device,
ctxt->sge[sge_no].addr))
goto err;
atomic_inc(&rdma->sc_dma_used);
ctxt->sge[sge_no].lkey = rdma->sc_dma_lkey;
} else {
ctxt->sge[sge_no].addr = (unsigned long)
vec->sge[sge_no].iov_base;
ctxt->sge[sge_no].lkey = vec->frmr->mr->lkey;
}
ctxt->sge[sge_no].length = sge_bytes;
}
BUG_ON(byte_count != 0);
/* Save all respages in the ctxt and remove them from the
* respages array. They are our pages until the I/O
* completes.
*/
for (page_no = 0; page_no < rqstp->rq_resused; page_no++) {
ctxt->pages[page_no+1] = rqstp->rq_respages[page_no];
ctxt->count++;
rqstp->rq_respages[page_no] = NULL;
/*
* If there are more pages than SGE, terminate SGE
* list so that svc_rdma_unmap_dma doesn't attempt to
* unmap garbage.
*/
if (page_no+1 >= sge_no)
ctxt->sge[page_no+1].length = 0;
}
BUG_ON(sge_no > rdma->sc_max_sge);
memset(&send_wr, 0, sizeof send_wr);
ctxt->wr_op = IB_WR_SEND;
send_wr.wr_id = (unsigned long)ctxt;
send_wr.sg_list = ctxt->sge;
send_wr.num_sge = sge_no;
send_wr.opcode = IB_WR_SEND;
send_wr.send_flags = IB_SEND_SIGNALED;
if (vec->frmr) {
/* Prepare INVALIDATE WR */
memset(&inv_wr, 0, sizeof inv_wr);
inv_wr.opcode = IB_WR_LOCAL_INV;
inv_wr.send_flags = IB_SEND_SIGNALED;
inv_wr.ex.invalidate_rkey =
vec->frmr->mr->lkey;
send_wr.next = &inv_wr;
}
ret = svc_rdma_send(rdma, &send_wr);
if (ret)
goto err;
return 0;
err:
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_frmr(rdma, vec->frmr);
svc_rdma_put_context(ctxt, 1);
return -EIO;
}
static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
u32 rmr, u64 to,
u32 xdr_off, int write_len,
struct svc_rdma_req_map *vec)
{
struct ib_send_wr write_wr;
struct ib_sge *sge;
int xdr_sge_no;
int sge_no;
int sge_bytes;
int sge_off;
int bc;
struct svc_rdma_op_ctxt *ctxt;
BUG_ON(vec->count > RPCSVC_MAXPAGES);
dprintk("svcrdma: RDMA_WRITE rmr=%x, to=%llx, xdr_off=%d, "
"write_len=%d, vec->sge=%p, vec->count=%lu\n",
rmr, (unsigned long long)to, xdr_off,
write_len, vec->sge, vec->count);
ctxt = svc_rdma_get_context(xprt);
ctxt->direction = DMA_TO_DEVICE;
sge = ctxt->sge;
/* Find the SGE associated with xdr_off */
for (bc = xdr_off, xdr_sge_no = 1; bc && xdr_sge_no < vec->count;
xdr_sge_no++) {
if (vec->sge[xdr_sge_no].iov_len > bc)
break;
bc -= vec->sge[xdr_sge_no].iov_len;
}
sge_off = bc;
bc = write_len;
sge_no = 0;
/* Copy the remaining SGE */
while (bc != 0) {
sge_bytes = min_t(size_t,
bc, vec->sge[xdr_sge_no].iov_len-sge_off);
sge[sge_no].length = sge_bytes;
if (!vec->frmr) {
sge[sge_no].addr =
ib_dma_map_single(xprt->sc_cm_id->device,
(void *)
vec->sge[xdr_sge_no].iov_base + sge_off,
sge_bytes, DMA_TO_DEVICE);
if (ib_dma_mapping_error(xprt->sc_cm_id->device,
sge[sge_no].addr))
goto err;
atomic_inc(&xprt->sc_dma_used);
sge[sge_no].lkey = xprt->sc_dma_lkey;
} else {
sge[sge_no].addr = (unsigned long)
vec->sge[xdr_sge_no].iov_base + sge_off;
sge[sge_no].lkey = vec->frmr->mr->lkey;
}
ctxt->count++;
ctxt->frmr = vec->frmr;
sge_off = 0;
sge_no++;
xdr_sge_no++;
BUG_ON(xdr_sge_no > vec->count);
bc -= sge_bytes;
}
/* Prepare WRITE WR */
memset(&write_wr, 0, sizeof write_wr);
ctxt->wr_op = IB_WR_RDMA_WRITE;
write_wr.wr_id = (unsigned long)ctxt;
write_wr.sg_list = &sge[0];
write_wr.num_sge = sge_no;
write_wr.opcode = IB_WR_RDMA_WRITE;
write_wr.send_flags = IB_SEND_SIGNALED;
write_wr.wr.rdma.rkey = rmr;
write_wr.wr.rdma.remote_addr = to;
/* Post It */
atomic_inc(&rdma_stat_write);
if (svc_rdma_send(xprt, &write_wr))
goto err;
return 0;
err:
svc_rdma_put_context(ctxt, 0);
/* Fatal error, close transport */
return -EIO;
}
/*
* Use RDMA_READ to read data from the advertised client buffer into the
* XDR stream starting at rq_arg.head[0].iov_base.
* Each chunk in the array
* contains the following fields:
* discrim - '1', This isn't used for data placement
* position - The xdr stream offset (the same for every chunk)
* handle - RMR for client memory region
* length - data transfer length
* offset - 64 bit tagged offset in remote memory region
*
* On our side, we need to read into a pagelist. The first page immediately
* follows the RPC header.
*
* This function returns:
* 0 - No error and no read-list found.
*
* 1 - Successful read-list processing. The data is not yet in
* the pagelist and therefore the RPC request must be deferred. The
* I/O completion will enqueue the transport again and
* svc_rdma_recvfrom will complete the request.
*
* <0 - Error processing/posting read-list.
*
* NOTE: The ctxt must not be touched after the last WR has been posted
* because the I/O completion processing may occur on another
* processor and free / modify the context. Ne touche pas!
*/
static int rdma_read_xdr(struct svcxprt_rdma *xprt,
struct rpcrdma_msg *rmsgp,
struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *hdr_ctxt)
{
struct ib_send_wr read_wr;
struct ib_send_wr inv_wr;
int err = 0;
int ch_no;
int ch_count;
int byte_count;
int sge_count;
u64 sgl_offset;
struct rpcrdma_read_chunk *ch;
struct svc_rdma_op_ctxt *ctxt = NULL;
struct svc_rdma_req_map *rpl_map;
struct svc_rdma_req_map *chl_map;
/* If no read list is present, return 0 */
ch = svc_rdma_get_read_chunk(rmsgp);
if (!ch)
return 0;
svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count);
if (ch_count > RPCSVC_MAXPAGES)
return -EINVAL;
/* Allocate temporary reply and chunk maps */
rpl_map = svc_rdma_get_req_map();
chl_map = svc_rdma_get_req_map();
if (!xprt->sc_frmr_pg_list_len)
sge_count = map_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
rpl_map, chl_map, ch_count,
byte_count);
else
sge_count = fast_reg_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
rpl_map, chl_map, ch_count,
byte_count);
if (sge_count < 0) {
err = -EIO;
goto out;
}
sgl_offset = 0;
ch_no = 0;
for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
ch->rc_discrim != 0; ch++, ch_no++) {
next_sge:
ctxt = svc_rdma_get_context(xprt);
ctxt->direction = DMA_FROM_DEVICE;
ctxt->frmr = hdr_ctxt->frmr;
ctxt->read_hdr = NULL;
clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
/* Prepare READ WR */
memset(&read_wr, 0, sizeof read_wr);
read_wr.wr_id = (unsigned long)ctxt;
read_wr.opcode = IB_WR_RDMA_READ;
ctxt->wr_op = read_wr.opcode;
read_wr.send_flags = IB_SEND_SIGNALED;
read_wr.wr.rdma.rkey = ch->rc_target.rs_handle;
read_wr.wr.rdma.remote_addr =
get_unaligned(&(ch->rc_target.rs_offset)) +
sgl_offset;
read_wr.sg_list = ctxt->sge;
read_wr.num_sge =
rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
err = rdma_set_ctxt_sge(xprt, ctxt, hdr_ctxt->frmr,
&rpl_map->sge[chl_map->ch[ch_no].start],
&sgl_offset,
read_wr.num_sge);
if (err) {
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
goto out;
}
if (((ch+1)->rc_discrim == 0) &&
(read_wr.num_sge == chl_map->ch[ch_no].count)) {
/*
* Mark the last RDMA_READ with a bit to
* indicate all RPC data has been fetched from
* the client and the RPC needs to be enqueued.
*/
set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
if (hdr_ctxt->frmr) {
set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
/*
* Invalidate the local MR used to map the data
* sink.
*/
if (xprt->sc_dev_caps &
SVCRDMA_DEVCAP_READ_W_INV) {
read_wr.opcode =
IB_WR_RDMA_READ_WITH_INV;
ctxt->wr_op = read_wr.opcode;
read_wr.ex.invalidate_rkey =
ctxt->frmr->mr->lkey;
} else {
/* Prepare INVALIDATE WR */
memset(&inv_wr, 0, sizeof inv_wr);
inv_wr.opcode = IB_WR_LOCAL_INV;
inv_wr.send_flags = IB_SEND_SIGNALED;
inv_wr.ex.invalidate_rkey =
hdr_ctxt->frmr->mr->lkey;
read_wr.next = &inv_wr;
}
}
ctxt->read_hdr = hdr_ctxt;
}
/* Post the read */
err = svc_rdma_send(xprt, &read_wr);
if (err) {
printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n",
err);
set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
goto out;
}
atomic_inc(&rdma_stat_read);
if (read_wr.num_sge < chl_map->ch[ch_no].count) {
chl_map->ch[ch_no].count -= read_wr.num_sge;
chl_map->ch[ch_no].start += read_wr.num_sge;
goto next_sge;
}
sgl_offset = 0;
err = 1;
}
out:
svc_rdma_put_req_map(rpl_map);
svc_rdma_put_req_map(chl_map);
/* Detach arg pages. svc_recv will replenish them */
for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++)
rqstp->rq_pages[ch_no] = NULL;
/*
* Detach res pages. svc_release must see a resused count of
* zero or it will attempt to put them.
*/
while (rqstp->rq_resused)
rqstp->rq_respages[--rqstp->rq_resused] = NULL;
return err;
}
/* Issue an RDMA_READ using an FRMR to map the data sink */
static int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *head,
int *page_no,
u32 *page_offset,
u32 rs_handle,
u32 rs_length,
u64 rs_offset,
int last)
{
struct ib_send_wr read_wr;
struct ib_send_wr inv_wr;
struct ib_send_wr fastreg_wr;
u8 key;
int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt);
int ret, read, pno;
u32 pg_off = *page_offset;
u32 pg_no = *page_no;
if (IS_ERR(frmr))
return -ENOMEM;
ctxt->direction = DMA_FROM_DEVICE;
ctxt->frmr = frmr;
pages_needed = min_t(int, pages_needed, xprt->sc_frmr_pg_list_len);
read = min_t(int, pages_needed << PAGE_SHIFT, rs_length);
frmr->kva = page_address(rqstp->rq_arg.pages[pg_no]);
frmr->direction = DMA_FROM_DEVICE;
frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE);
frmr->map_len = pages_needed << PAGE_SHIFT;
frmr->page_list_len = pages_needed;
for (pno = 0; pno < pages_needed; pno++) {
int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
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++;
rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,8,0))
rqstp->rq_next_page = rqstp->rq_respages + 1;
#endif
frmr->page_list->page_list[pno] =
ib_dma_map_page(xprt->sc_cm_id->device,
head->arg.pages[pg_no], 0,
PAGE_SIZE, DMA_FROM_DEVICE);
ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
frmr->page_list->page_list[pno]);
if (ret)
goto err;
atomic_inc(&xprt->sc_dma_used);
/* adjust offset and wrap to next page if needed */
pg_off += len;
if (pg_off == PAGE_SIZE) {
pg_off = 0;
pg_no++;
}
rs_length -= len;
}
if (last && rs_length == 0)
set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
else
clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
/* Bump the key */
key = (u8)(frmr->mr->lkey & 0x000000FF);
ib_update_fast_reg_key(frmr->mr, ++key);
ctxt->sge[0].addr = (unsigned long)frmr->kva + *page_offset;
ctxt->sge[0].lkey = frmr->mr->lkey;
ctxt->sge[0].length = read;
ctxt->count = 1;
ctxt->read_hdr = head;
/* Prepare FASTREG WR */
memset(&fastreg_wr, 0, sizeof(fastreg_wr));
fastreg_wr.opcode = IB_WR_FAST_REG_MR;
fastreg_wr.send_flags = IB_SEND_SIGNALED;
fastreg_wr.wr.fast_reg.iova_start = (unsigned long)frmr->kva;
fastreg_wr.wr.fast_reg.page_list = frmr->page_list;
fastreg_wr.wr.fast_reg.page_list_len = frmr->page_list_len;
fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
fastreg_wr.wr.fast_reg.length = frmr->map_len;
fastreg_wr.wr.fast_reg.access_flags = frmr->access_flags;
fastreg_wr.wr.fast_reg.rkey = frmr->mr->lkey;
fastreg_wr.next = &read_wr;
/* Prepare RDMA_READ */
memset(&read_wr, 0, sizeof(read_wr));
read_wr.send_flags = IB_SEND_SIGNALED;
read_wr.wr.rdma.rkey = rs_handle;
read_wr.wr.rdma.remote_addr = rs_offset;
read_wr.sg_list = ctxt->sge;
read_wr.num_sge = 1;
if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) {
read_wr.opcode = IB_WR_RDMA_READ_WITH_INV;
read_wr.wr_id = (unsigned long)ctxt;
read_wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey;
} else {
read_wr.opcode = IB_WR_RDMA_READ;
read_wr.next = &inv_wr;
/* Prepare invalidate */
memset(&inv_wr, 0, sizeof(inv_wr));
inv_wr.wr_id = (unsigned long)ctxt;
inv_wr.opcode = IB_WR_LOCAL_INV;
inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE;
inv_wr.ex.invalidate_rkey = frmr->mr->lkey;
}
ctxt->wr_op = read_wr.opcode;
/* Post the chain */
ret = svc_rdma_send(xprt, &fastreg_wr);
if (ret) {
pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
goto err;
}
/* return current location in page array */
*page_no = pg_no;
*page_offset = pg_off;
ret = read;
atomic_inc(&rdma_stat_read);
return ret;
err:
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
svc_rdma_put_frmr(xprt, frmr);
return ret;
}
/* Issue an RDMA_READ using the local lkey to map the data sink */
static int rdma_read_chunk_lcl(struct svcxprt_rdma *xprt,
struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *head,
int *page_no,
u32 *page_offset,
u32 rs_handle,
u32 rs_length,
u64 rs_offset,
int last)
{
struct ib_send_wr read_wr;
int pages_needed = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
int ret, read, pno;
u32 pg_off = *page_offset;
u32 pg_no = *page_no;
ctxt->direction = DMA_FROM_DEVICE;
ctxt->read_hdr = head;
pages_needed =
min_t(int, pages_needed, rdma_read_max_sge(xprt, pages_needed));
read = min_t(int, pages_needed << PAGE_SHIFT, rs_length);
for (pno = 0; pno < pages_needed; pno++) {
int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
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++;
rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
#if (LINUX_VERSION_CODE >= KERNEL_VERSION(3,8,0))
rqstp->rq_next_page = rqstp->rq_respages + 1;
#endif
ctxt->sge[pno].addr =
ib_dma_map_page(xprt->sc_cm_id->device,
head->arg.pages[pg_no], pg_off,
PAGE_SIZE - pg_off,
DMA_FROM_DEVICE);
ret = ib_dma_mapping_error(xprt->sc_cm_id->device,
ctxt->sge[pno].addr);
if (ret)
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].length = len;
ctxt->count++;
/* adjust offset and wrap to next page if needed */
pg_off += len;
if (pg_off == PAGE_SIZE) {
pg_off = 0;
pg_no++;
}
rs_length -= len;
}
if (last && rs_length == 0)
set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
else
clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
memset(&read_wr, 0, sizeof(read_wr));
read_wr.wr_id = (unsigned long)ctxt;
read_wr.opcode = IB_WR_RDMA_READ;
ctxt->wr_op = read_wr.opcode;
read_wr.send_flags = IB_SEND_SIGNALED;
read_wr.wr.rdma.rkey = rs_handle;
read_wr.wr.rdma.remote_addr = rs_offset;
read_wr.sg_list = ctxt->sge;
read_wr.num_sge = pages_needed;
ret = svc_rdma_send(xprt, &read_wr);
if (ret) {
pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
goto err;
}
/* return current location in page array */
*page_no = pg_no;
*page_offset = pg_off;
ret = read;
atomic_inc(&rdma_stat_read);
return ret;
err:
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
return ret;
}
static int rdma_read_xdr(struct svcxprt_rdma *xprt,
struct rpcrdma_msg *rmsgp,
struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *hdr_ctxt)
{
struct ib_send_wr read_wr;
struct ib_send_wr inv_wr;
int err = 0;
int ch_no;
int ch_count;
int byte_count;
int sge_count;
u64 sgl_offset;
struct rpcrdma_read_chunk *ch;
struct svc_rdma_op_ctxt *ctxt = NULL;
struct svc_rdma_req_map *rpl_map;
struct svc_rdma_req_map *chl_map;
/* */
ch = svc_rdma_get_read_chunk(rmsgp);
if (!ch)
return 0;
svc_rdma_rcl_chunk_counts(ch, &ch_count, &byte_count);
if (ch_count > RPCSVC_MAXPAGES)
return -EINVAL;
/* */
rpl_map = svc_rdma_get_req_map();
chl_map = svc_rdma_get_req_map();
if (!xprt->sc_frmr_pg_list_len)
sge_count = map_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
rpl_map, chl_map, ch_count,
byte_count);
else
sge_count = fast_reg_read_chunks(xprt, rqstp, hdr_ctxt, rmsgp,
rpl_map, chl_map, ch_count,
byte_count);
if (sge_count < 0) {
err = -EIO;
goto out;
}
sgl_offset = 0;
ch_no = 0;
for (ch = (struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
ch->rc_discrim != 0; ch++, ch_no++) {
u64 rs_offset;
next_sge:
ctxt = svc_rdma_get_context(xprt);
ctxt->direction = DMA_FROM_DEVICE;
ctxt->frmr = hdr_ctxt->frmr;
ctxt->read_hdr = NULL;
clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
clear_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
/* */
memset(&read_wr, 0, sizeof read_wr);
read_wr.wr_id = (unsigned long)ctxt;
read_wr.opcode = IB_WR_RDMA_READ;
ctxt->wr_op = read_wr.opcode;
read_wr.send_flags = IB_SEND_SIGNALED;
read_wr.wr.rdma.rkey = ntohl(ch->rc_target.rs_handle);
xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
&rs_offset);
read_wr.wr.rdma.remote_addr = rs_offset + sgl_offset;
read_wr.sg_list = ctxt->sge;
read_wr.num_sge =
rdma_read_max_sge(xprt, chl_map->ch[ch_no].count);
err = rdma_set_ctxt_sge(xprt, ctxt, hdr_ctxt->frmr,
&rpl_map->sge[chl_map->ch[ch_no].start],
&sgl_offset,
read_wr.num_sge);
if (err) {
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
goto out;
}
if (((ch+1)->rc_discrim == 0) &&
(read_wr.num_sge == chl_map->ch[ch_no].count)) {
/*
*/
set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
if (hdr_ctxt->frmr) {
set_bit(RDMACTXT_F_FAST_UNREG, &ctxt->flags);
/*
*/
if (xprt->sc_dev_caps &
SVCRDMA_DEVCAP_READ_W_INV) {
read_wr.opcode =
IB_WR_RDMA_READ_WITH_INV;
ctxt->wr_op = read_wr.opcode;
read_wr.ex.invalidate_rkey =
ctxt->frmr->mr->lkey;
} else {
/* */
memset(&inv_wr, 0, sizeof inv_wr);
inv_wr.opcode = IB_WR_LOCAL_INV;
inv_wr.send_flags = IB_SEND_SIGNALED;
inv_wr.ex.invalidate_rkey =
hdr_ctxt->frmr->mr->lkey;
read_wr.next = &inv_wr;
}
}
ctxt->read_hdr = hdr_ctxt;
}
/* */
err = svc_rdma_send(xprt, &read_wr);
if (err) {
printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n",
err);
set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
goto out;
}
atomic_inc(&rdma_stat_read);
if (read_wr.num_sge < chl_map->ch[ch_no].count) {
chl_map->ch[ch_no].count -= read_wr.num_sge;
chl_map->ch[ch_no].start += read_wr.num_sge;
goto next_sge;
}
sgl_offset = 0;
err = 1;
}
out:
svc_rdma_put_req_map(rpl_map);
svc_rdma_put_req_map(chl_map);
/* */
for (ch_no = 0; &rqstp->rq_pages[ch_no] < rqstp->rq_respages; ch_no++)
rqstp->rq_pages[ch_no] = NULL;
/*
*/
while (rqstp->rq_resused)
rqstp->rq_respages[--rqstp->rq_resused] = NULL;
return err;
}
/* This function prepares the portion of the RPCRDMA message to be
* sent in the RDMA_SEND. This function is called after data sent via
* RDMA has already been transmitted. There are three cases:
* - The RPCRDMA header, RPC header, and payload are all sent in a
* single RDMA_SEND. This is the "inline" case.
* - The RPCRDMA header and some portion of the RPC header and data
* are sent via this RDMA_SEND and another portion of the data is
* sent via RDMA.
* - The RPCRDMA header [NOMSG] is sent in this RDMA_SEND and the RPC
* header and data are all transmitted via RDMA.
* In all three cases, this function prepares the RPCRDMA header in
* sge[0], the 'type' parameter indicates the type to place in the
* RPCRDMA header, and the 'byte_count' field indicates how much of
* the XDR to include in this RDMA_SEND.
*/
static int send_reply(struct svcxprt_rdma *rdma,
struct svc_rqst *rqstp,
struct page *page,
struct rpcrdma_msg *rdma_resp,
struct svc_rdma_op_ctxt *ctxt,
struct svc_rdma_req_map *vec,
int byte_count)
{
struct ib_send_wr send_wr;
int sge_no;
int sge_bytes;
int page_no;
int ret;
/* Post a recv buffer to handle another request. */
ret = svc_rdma_post_recv(rdma);
if (ret) {
printk(KERN_INFO
"svcrdma: could not post a receive buffer, err=%d."
"Closing transport %p.\n", ret, rdma);
set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags);
svc_rdma_put_context(ctxt, 0);
return -ENOTCONN;
}
/* Prepare the context */
ctxt->pages[0] = page;
ctxt->count = 1;
/* Prepare the SGE for the RPCRDMA Header */
atomic_inc(&rdma->sc_dma_used);
ctxt->sge[0].addr =
ib_dma_map_page(rdma->sc_cm_id->device,
page, 0, PAGE_SIZE, DMA_TO_DEVICE);
ctxt->direction = DMA_TO_DEVICE;
ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
ctxt->sge[0].lkey = rdma->sc_phys_mr->lkey;
/* Determine how many of our SGE are to be transmitted */
for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
byte_count -= sge_bytes;
atomic_inc(&rdma->sc_dma_used);
ctxt->sge[sge_no].addr =
ib_dma_map_single(rdma->sc_cm_id->device,
vec->sge[sge_no].iov_base,
sge_bytes, DMA_TO_DEVICE);
ctxt->sge[sge_no].length = sge_bytes;
ctxt->sge[sge_no].lkey = rdma->sc_phys_mr->lkey;
}
BUG_ON(byte_count != 0);
/* Save all respages in the ctxt and remove them from the
* respages array. They are our pages until the I/O
* completes.
*/
for (page_no = 0; page_no < rqstp->rq_resused; page_no++) {
ctxt->pages[page_no+1] = rqstp->rq_respages[page_no];
ctxt->count++;
rqstp->rq_respages[page_no] = NULL;
/* If there are more pages than SGE, terminate SGE list */
if (page_no+1 >= sge_no)
ctxt->sge[page_no+1].length = 0;
}
BUG_ON(sge_no > rdma->sc_max_sge);
memset(&send_wr, 0, sizeof send_wr);
ctxt->wr_op = IB_WR_SEND;
send_wr.wr_id = (unsigned long)ctxt;
send_wr.sg_list = ctxt->sge;
send_wr.num_sge = sge_no;
send_wr.opcode = IB_WR_SEND;
send_wr.send_flags = IB_SEND_SIGNALED;
ret = svc_rdma_send(rdma, &send_wr);
if (ret)
svc_rdma_put_context(ctxt, 1);
return ret;
}
/* Issue an RDMA_READ using an FRMR to map the data sink */
int rdma_read_chunk_frmr(struct svcxprt_rdma *xprt,
struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *head,
int *page_no,
u32 *page_offset,
u32 rs_handle,
u32 rs_length,
u64 rs_offset,
bool last)
{
struct ib_rdma_wr read_wr;
struct ib_send_wr inv_wr;
struct ib_reg_wr reg_wr;
u8 key;
int nents = PAGE_ALIGN(*page_offset + rs_length) >> PAGE_SHIFT;
struct svc_rdma_op_ctxt *ctxt = svc_rdma_get_context(xprt);
struct svc_rdma_fastreg_mr *frmr = svc_rdma_get_frmr(xprt);
int ret, read, pno, dma_nents, n;
u32 pg_off = *page_offset;
u32 pg_no = *page_no;
if (IS_ERR(frmr))
return -ENOMEM;
ctxt->direction = DMA_FROM_DEVICE;
ctxt->frmr = frmr;
nents = min_t(unsigned int, nents, xprt->sc_frmr_pg_list_len);
read = min_t(int, (nents << PAGE_SHIFT) - *page_offset, rs_length);
frmr->direction = DMA_FROM_DEVICE;
frmr->access_flags = (IB_ACCESS_LOCAL_WRITE|IB_ACCESS_REMOTE_WRITE);
frmr->sg_nents = nents;
for (pno = 0; pno < nents; pno++) {
int len = min_t(int, rs_length, PAGE_SIZE - pg_off);
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++;
sg_set_page(&frmr->sg[pno], rqstp->rq_arg.pages[pg_no],
len, pg_off);
rqstp->rq_respages = &rqstp->rq_arg.pages[pg_no+1];
rqstp->rq_next_page = rqstp->rq_respages + 1;
/* adjust offset and wrap to next page if needed */
pg_off += len;
if (pg_off == PAGE_SIZE) {
pg_off = 0;
pg_no++;
}
rs_length -= len;
}
if (last && rs_length == 0)
set_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
else
clear_bit(RDMACTXT_F_LAST_CTXT, &ctxt->flags);
dma_nents = ib_dma_map_sg(xprt->sc_cm_id->device,
frmr->sg, frmr->sg_nents,
frmr->direction);
if (!dma_nents) {
pr_err("svcrdma: failed to dma map sg %p\n",
frmr->sg);
return -ENOMEM;
}
atomic_inc(&xprt->sc_dma_used);
n = ib_map_mr_sg(frmr->mr, frmr->sg, frmr->sg_nents, PAGE_SIZE);
if (unlikely(n != frmr->sg_nents)) {
pr_err("svcrdma: failed to map mr %p (%d/%d elements)\n",
frmr->mr, n, frmr->sg_nents);
return n < 0 ? n : -EINVAL;
}
/* Bump the key */
key = (u8)(frmr->mr->lkey & 0x000000FF);
ib_update_fast_reg_key(frmr->mr, ++key);
ctxt->sge[0].addr = frmr->mr->iova;
ctxt->sge[0].lkey = frmr->mr->lkey;
ctxt->sge[0].length = frmr->mr->length;
ctxt->count = 1;
ctxt->read_hdr = head;
/* Prepare REG WR */
reg_wr.wr.opcode = IB_WR_REG_MR;
reg_wr.wr.wr_id = 0;
reg_wr.wr.send_flags = IB_SEND_SIGNALED;
reg_wr.wr.num_sge = 0;
reg_wr.mr = frmr->mr;
reg_wr.key = frmr->mr->lkey;
reg_wr.access = frmr->access_flags;
reg_wr.wr.next = &read_wr.wr;
/* Prepare RDMA_READ */
memset(&read_wr, 0, sizeof(read_wr));
read_wr.wr.send_flags = IB_SEND_SIGNALED;
read_wr.rkey = rs_handle;
read_wr.remote_addr = rs_offset;
read_wr.wr.sg_list = ctxt->sge;
read_wr.wr.num_sge = 1;
if (xprt->sc_dev_caps & SVCRDMA_DEVCAP_READ_W_INV) {
read_wr.wr.opcode = IB_WR_RDMA_READ_WITH_INV;
read_wr.wr.wr_id = (unsigned long)ctxt;
read_wr.wr.ex.invalidate_rkey = ctxt->frmr->mr->lkey;
} else {
read_wr.wr.opcode = IB_WR_RDMA_READ;
read_wr.wr.next = &inv_wr;
/* Prepare invalidate */
memset(&inv_wr, 0, sizeof(inv_wr));
inv_wr.wr_id = (unsigned long)ctxt;
inv_wr.opcode = IB_WR_LOCAL_INV;
inv_wr.send_flags = IB_SEND_SIGNALED | IB_SEND_FENCE;
inv_wr.ex.invalidate_rkey = frmr->mr->lkey;
}
ctxt->wr_op = read_wr.wr.opcode;
/* Post the chain */
ret = svc_rdma_send(xprt, ®_wr.wr);
if (ret) {
pr_err("svcrdma: Error %d posting RDMA_READ\n", ret);
set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
goto err;
}
/* return current location in page array */
*page_no = pg_no;
*page_offset = pg_off;
ret = read;
atomic_inc(&rdma_stat_read);
return ret;
err:
ib_dma_unmap_sg(xprt->sc_cm_id->device,
frmr->sg, frmr->sg_nents, frmr->direction);
svc_rdma_put_context(ctxt, 0);
svc_rdma_put_frmr(xprt, frmr);
return ret;
}