Skip to content

L
linux
Commit cafc7398 authored by Chuck Lever's avatar Chuck Lever Committed by J. Bruce Fields
Browse files
Options

svcrdma: Use generic RDMA R/W API in RPC Call path 

The current svcrdma recvfrom code path has a lot of detail about
registration mode and the type of port (iWARP, IB, etc).

Instead, use the RDMA core's generic R/W API. This shares code with
other RDMA-enabled ULPs that manages the gory details of buffer
registration and the posting of RDMA Read Work Requests.

Since the Read list marshaling code is being replaced, I took the
opportunity to replace C structure-based XDR encoding code with more
portable code that uses pointer arithmetic.
Signed-off-by: default avatarChuck Lever <chuck.lever@oracle.com>
Signed-off-by: default avatarJ. Bruce Fields <bfields@redhat.com>
parent 026d958b
Hide whitespace changes
Inline Side-by-side
Showing with 106 additions and 468 deletions
include/linux/sunrpc/svc_rdma.h
View file @ cafc7398
......@@ -82,10 +82,7 @@ struct svc_rdma_op_ctxt {
int hdr_count;
struct xdr_buf arg;
struct ib_cqe cqe;
struct ib_cqe reg_cqe;
struct ib_cqe inv_cqe;
u32 byte_len;
u32 position;
struct svcxprt_rdma *xprt;
unsigned long flags;
enum dma_data_direction direction;
......@@ -116,7 +113,6 @@ struct svcxprt_rdma {
struct list_head sc_accept_q; /* Conn. waiting accept */
int sc_ord; /* RDMA read limit */
int sc_max_sge;
int sc_max_sge_rd; /* max sge for read target */
bool sc_snd_w_inv; /* OK to use Send With Invalidate */
atomic_t sc_sq_avail; /* SQEs ready to be consumed */
......@@ -141,10 +137,6 @@ struct svcxprt_rdma {
struct ib_qp *sc_qp;
struct ib_cq *sc_rq_cq;
struct ib_cq *sc_sq_cq;
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 */
unsigned int sc_frmr_pg_list_len;
struct list_head sc_frmr_q;
......@@ -187,12 +179,6 @@ extern int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt,
/* svc_rdma_recvfrom.c */
extern int svc_rdma_recvfrom(struct svc_rqst *);
extern int rdma_read_chunk_lcl(struct svcxprt_rdma *, struct svc_rqst *,
struct svc_rdma_op_ctxt *, int *, u32 *,
u32, u32, u64, bool);
extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
struct svc_rdma_op_ctxt *, int *, u32 *,
u32, u32, u64, bool);
/* svc_rdma_rw.c */
extern void svc_rdma_destroy_rw_ctxts(struct svcxprt_rdma *rdma);
......
net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
View file @ cafc7398
......@@ -41,13 +41,66 @@
* Author: Tom Tucker <tom@opengridcomputing.com>
*/
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/debug.h>
#include <linux/sunrpc/rpc_rdma.h>
#include <linux/spinlock.h>
/* Operation
*
* The main entry point is svc_rdma_recvfrom. This is called from
* svc_recv when the transport indicates there is incoming data to
* be read. "Data Ready" is signaled when an RDMA Receive completes,
* or when a set of RDMA Reads complete.
*
* An svc_rqst is passed in. This structure contains an array of
* free pages (rq_pages) that will contain the incoming RPC message.
*
* Short messages are moved directly into svc_rqst::rq_arg, and
* the RPC Call is ready to be processed by the Upper Layer.
* svc_rdma_recvfrom returns the length of the RPC Call message,
* completing the reception of the RPC Call.
*
* However, when an incoming message has Read chunks,
* svc_rdma_recvfrom must post RDMA Reads to pull the RPC Call's
* data payload from the client. svc_rdma_recvfrom sets up the
* RDMA Reads using pages in svc_rqst::rq_pages, which are
* transferred to an svc_rdma_op_ctxt for the duration of the
* I/O. svc_rdma_recvfrom then returns zero, since the RPC message
* is still not yet ready.
*
* When the Read chunk payloads have become available on the
* server, "Data Ready" is raised again, and svc_recv calls
* svc_rdma_recvfrom again. This second call may use a different
* svc_rqst than the first one, thus any information that needs
* to be preserved across these two calls is kept in an
* svc_rdma_op_ctxt.
*
* The second call to svc_rdma_recvfrom performs final assembly
* of the RPC Call message, using the RDMA Read sink pages kept in
* the svc_rdma_op_ctxt. The xdr_buf is copied from the
* svc_rdma_op_ctxt to the second svc_rqst. The second call returns
* the length of the completed RPC Call message.
*
* Page Management
*
* Pages under I/O must be transferred from the first svc_rqst to an
* svc_rdma_op_ctxt before the first svc_rdma_recvfrom call returns.
*
* The first svc_rqst supplies pages for RDMA Reads. These are moved
* from rqstp::rq_pages into ctxt::pages. The consumed elements of
* the rq_pages array are set to NULL and refilled with the first
* svc_rdma_recvfrom call returns.
*
* During the second svc_rdma_recvfrom call, RDMA Read sink pages
* are transferred from the svc_rdma_op_ctxt to the second svc_rqst
* (see rdma_read_complete() below).
*/
#include <asm/unaligned.h>
#include <rdma/ib_verbs.h>
#include <rdma/rdma_cm.h>
#include <linux/spinlock.h>
#include <linux/sunrpc/xdr.h>
#include <linux/sunrpc/debug.h>
#include <linux/sunrpc/rpc_rdma.h>
#include <linux/sunrpc/svc_rdma.h>
#define RPCDBG_FACILITY RPCDBG_SVCXPRT
......@@ -61,7 +114,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *ctxt,
u32 byte_count)
{
struct rpcrdma_msg *rmsgp;
struct page *page;
u32 bc;
int sge_no;
......@@ -85,13 +137,6 @@ static void rdma_build_arg_xdr(struct svc_rqst *rqstp,
rqstp->rq_arg.page_len = bc;
rqstp->rq_arg.page_base = 0;
/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
if (rmsgp->rm_type == rdma_nomsg)
rqstp->rq_arg.pages = &rqstp->rq_pages[0];
else
rqstp->rq_arg.pages = &rqstp->rq_pages[1];
sge_no = 1;
while (bc && sge_no < ctxt->count) {
page = ctxt->pages[sge_no];
......@@ -320,395 +365,6 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg)
return -EINVAL;
}
/* Issue an RDMA_READ using the local lkey to map the data sink */
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,
bool last)
{
struct ib_rdma_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, xprt->sc_max_sge_rd);
read = min_t(int, (pages_needed << PAGE_SHIFT) - *page_offset,
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];
rqstp->rq_next_page = rqstp->rq_respages + 1;
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;
svc_rdma_count_mappings(xprt, ctxt);
ctxt->sge[pno].lkey = xprt->sc_pd->local_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));
ctxt->cqe.done = svc_rdma_wc_read;
read_wr.wr.wr_cqe = &ctxt->cqe;
read_wr.wr.opcode = IB_WR_RDMA_READ;
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 = pages_needed;
ret = svc_rdma_send(xprt, &read_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:
svc_rdma_unmap_dma(ctxt);
svc_rdma_put_context(ctxt, 0);
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;
}
n = ib_map_mr_sg(frmr->mr, frmr->sg, frmr->sg_nents, NULL, 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 */
ctxt->reg_cqe.done = svc_rdma_wc_reg;
reg_wr.wr.wr_cqe = &ctxt->reg_cqe;
reg_wr.wr.opcode = IB_WR_REG_MR;
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));
ctxt->cqe.done = svc_rdma_wc_read;
read_wr.wr.wr_cqe = &ctxt->cqe;
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.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));
ctxt->inv_cqe.done = svc_rdma_wc_inv;
inv_wr.wr_cqe = &ctxt->inv_cqe;
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;
}
/* Post the chain */
ret = svc_rdma_send(xprt, &reg_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:
svc_rdma_put_context(ctxt, 0);
svc_rdma_put_frmr(xprt, frmr);
return ret;
}
/* If there was additional inline content, append it to the end of arg.pages.
* Tail copy has to be done after the reader function has determined how many
* pages are needed for RDMA READ.
*/
static int
rdma_copy_tail(struct svc_rqst *rqstp, struct svc_rdma_op_ctxt *head,
u32 position, u32 byte_count, u32 page_offset, int page_no)
{
char *srcp, *destp;
srcp = head->arg.head[0].iov_base + position;
byte_count = head->arg.head[0].iov_len - position;
if (byte_count > PAGE_SIZE) {
dprintk("svcrdma: large tail unsupported\n");
return 0;
}
/* Fit as much of the tail on the current page as possible */
if (page_offset != PAGE_SIZE) {
destp = page_address(rqstp->rq_arg.pages[page_no]);
destp += page_offset;
while (byte_count--) {
*destp++ = *srcp++;
page_offset++;
if (page_offset == PAGE_SIZE && byte_count)
goto more;
}
goto done;
}
more:
/* Fit the rest on the next page */
page_no++;
destp = page_address(rqstp->rq_arg.pages[page_no]);
while (byte_count--)
*destp++ = *srcp++;
rqstp->rq_respages = &rqstp->rq_arg.pages[page_no+1];
rqstp->rq_next_page = rqstp->rq_respages + 1;
done:
byte_count = head->arg.head[0].iov_len - position;
head->arg.page_len += byte_count;
head->arg.len += byte_count;
head->arg.buflen += byte_count;
return 1;
}
/* Returns the address of the first read chunk or <nul> if no read chunk
* is present
*/
static struct rpcrdma_read_chunk *
svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp)
{
struct rpcrdma_read_chunk *ch =
(struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
if (ch->rc_discrim == xdr_zero)
return NULL;
return ch;
}
static int rdma_read_chunks(struct svcxprt_rdma *xprt,
struct rpcrdma_msg *rmsgp,
struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *head)
{
int page_no, ret;
struct rpcrdma_read_chunk *ch;
u32 handle, page_offset, byte_count;
u32 position;
u64 rs_offset;
bool last;
/* If no read list is present, return 0 */
ch = svc_rdma_get_read_chunk(rmsgp);
if (!ch)
return 0;
/* The request is completed when the RDMA_READs complete. The
* head context keeps all the pages that comprise the
* request.
*/
head->arg.head[0] = rqstp->rq_arg.head[0];
head->arg.tail[0] = rqstp->rq_arg.tail[0];
head->hdr_count = head->count;
head->arg.page_base = 0;
head->arg.page_len = 0;
head->arg.len = rqstp->rq_arg.len;
head->arg.buflen = rqstp->rq_arg.buflen;
/* RDMA_NOMSG: RDMA READ data should land just after RDMA RECV data */
position = be32_to_cpu(ch->rc_position);
if (position == 0) {
head->arg.pages = &head->pages[0];
page_offset = head->byte_len;
} else {
head->arg.pages = &head->pages[head->count];
page_offset = 0;
}
ret = 0;
page_no = 0;
for (; ch->rc_discrim != xdr_zero; ch++) {
if (be32_to_cpu(ch->rc_position) != position)
goto err;
handle = be32_to_cpu(ch->rc_target.rs_handle),
byte_count = be32_to_cpu(ch->rc_target.rs_length);
xdr_decode_hyper((__be32 *)&ch->rc_target.rs_offset,
&rs_offset);
while (byte_count > 0) {
last = (ch + 1)->rc_discrim == xdr_zero;
ret = xprt->sc_reader(xprt, rqstp, head,
&page_no, &page_offset,
handle, byte_count,
rs_offset, last);
if (ret < 0)
goto err;
byte_count -= ret;
rs_offset += ret;
head->arg.buflen += ret;
}
}
/* Read list may need XDR round-up (see RFC 5666, s. 3.7) */
if (page_offset & 3) {
u32 pad = 4 - (page_offset & 3);
head->arg.tail[0].iov_len += pad;
head->arg.len += pad;
head->arg.buflen += pad;
page_offset += pad;
}
ret = 1;
if (position && position < head->arg.head[0].iov_len)
ret = rdma_copy_tail(rqstp, head, position,
byte_count, page_offset, page_no);
head->arg.head[0].iov_len = position;
head->position = position;
err:
/* Detach arg pages. svc_recv will replenish them */
for (page_no = 0;
&rqstp->rq_pages[page_no] < rqstp->rq_respages; page_no++)
rqstp->rq_pages[page_no] = NULL;
return ret;
}
static void rdma_read_complete(struct svc_rqst *rqstp,
struct svc_rdma_op_ctxt *head)
{
......@@ -720,24 +376,9 @@ static void rdma_read_complete(struct svc_rqst *rqstp,
rqstp->rq_pages[page_no] = head->pages[page_no];
}
/* Adjustments made for RDMA_NOMSG type requests */
if (head->position == 0) {
if (head->arg.len <= head->sge[0].length) {
head->arg.head[0].iov_len = head->arg.len -
head->byte_len;
head->arg.page_len = 0;
} else {
head->arg.head[0].iov_len = head->sge[0].length -
head->byte_len;
head->arg.page_len = head->arg.len -
head->sge[0].length;
}
}
/* Point rq_arg.pages past header */
rqstp->rq_arg.pages = &rqstp->rq_pages[head->hdr_count];
rqstp->rq_arg.page_len = head->arg.page_len;
rqstp->rq_arg.page_base = head->arg.page_base;
/* rq_respages starts after the last arg page */
rqstp->rq_respages = &rqstp->rq_pages[page_no];
......@@ -834,10 +475,35 @@ static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt,
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
* request.
/**
* svc_rdma_recvfrom - Receive an RPC call
* @rqstp: request structure into which to receive an RPC Call
*
* Returns:
* The positive number of bytes in the RPC Call message,
* %0 if there were no Calls ready to return,
* %-EINVAL if the Read chunk data is too large,
* %-ENOMEM if rdma_rw context pool was exhausted,
* %-ENOTCONN if posting failed (connection is lost),
* %-EIO if rdma_rw initialization failed (DMA mapping, etc).
*
* Called in a loop when XPT_DATA is set. XPT_DATA is cleared only
* when there are no remaining ctxt's to process.
*
* The next ctxt is removed from the "receive" lists.
*
* - If the ctxt completes a Read, then finish assembling the Call
* message and return the number of bytes in the message.
*
* - If the ctxt completes a Receive, then construct the Call
* message from the contents of the Receive buffer.
*
* - If there are no Read chunks in this message, then finish
* assembling the Call message and return the number of bytes
* in the message.
*
* - If there are Read chunks in this message, post Read WRs to
* pull that payload and return 0.
*/
int svc_rdma_recvfrom(struct svc_rqst *rqstp)
{
......@@ -845,11 +511,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
struct svcxprt_rdma *rdma_xprt =
container_of(xprt, struct svcxprt_rdma, sc_xprt);
struct svc_rdma_op_ctxt *ctxt;
struct rpcrdma_msg *rmsgp;
__be32 *p;
int ret;
dprintk("svcrdma: rqstp=%p\n", rqstp);
spin_lock(&rdma_xprt->sc_rq_dto_lock);
if (!list_empty(&rdma_xprt->sc_read_complete_q)) {
ctxt = list_first_entry(&rdma_xprt->sc_read_complete_q,
......@@ -870,7 +534,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
}
spin_unlock(&rdma_xprt->sc_rq_dto_lock);
dprintk("svcrdma: processing ctxt=%p on xprt=%p, rqstp=%p\n",
dprintk("svcrdma: recvfrom: ctxt=%p on xprt=%p, rqstp=%p\n",
ctxt, rdma_xprt, rqstp);
atomic_inc(&rdma_stat_recv);
......@@ -878,7 +542,7 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
rdma_build_arg_xdr(rqstp, ctxt, ctxt->byte_len);
/* Decode the RDMA header. */
rmsgp = (struct rpcrdma_msg *)rqstp->rq_arg.head[0].iov_base;
p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg);
if (ret < 0)
goto out_err;
......@@ -886,9 +550,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
goto out_drop;
rqstp->rq_xprt_hlen = ret;
if (svc_rdma_is_backchannel_reply(xprt, &rmsgp->rm_xid)) {
ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt,
&rmsgp->rm_xid,
if (svc_rdma_is_backchannel_reply(xprt, p)) {
ret = svc_rdma_handle_bc_reply(xprt->xpt_bc_xprt, p,
&rqstp->rq_arg);
svc_rdma_put_context(ctxt, 0);
if (ret)
......@@ -896,16 +559,9 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
return ret;
}
/* Read read-list data. */
ret = rdma_read_chunks(rdma_xprt, rmsgp, rqstp, ctxt);
if (ret > 0) {
/* read-list posted, defer until data received from client. */
goto defer;
} else if (ret < 0) {
/* Post of read-list failed, free context. */
svc_rdma_put_context(ctxt, 1);
return 0;
}
p += rpcrdma_fixed_maxsz;
if (*p != xdr_zero)
goto out_readchunk;
complete:
ret = rqstp->rq_arg.head[0].iov_len
......@@ -921,13 +577,22 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
svc_xprt_copy_addrs(rqstp, xprt);
return ret;
out_readchunk:
ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p);
if (ret < 0)
goto out_postfail;
return 0;
out_err:
svc_rdma_send_error(rdma_xprt, &rmsgp->rm_xid, ret);
svc_rdma_send_error(rdma_xprt, p, ret);
svc_rdma_put_context(ctxt, 0);
return 0;
defer:
return 0;
out_postfail:
if (ret == -EINVAL)
svc_rdma_send_error(rdma_xprt, p, ret);
svc_rdma_put_context(ctxt, 1);
return ret;
out_drop:
svc_rdma_put_context(ctxt, 1);
......
net/sunrpc/xprtrdma/svc_rdma_transport.c
View file @ cafc7398
......@@ -908,8 +908,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
* capabilities of this particular device */
newxprt->sc_max_sge = min((size_t)dev->attrs.max_sge,
(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_t(u32, dev->attrs.max_qp_wr,
svcrdma_max_requests);
......@@ -998,12 +996,10 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
* NB: iWARP requires remote write access for the data sink
* of an RDMA_READ. IB does not.
*/
newxprt->sc_reader = rdma_read_chunk_lcl;
if (dev->attrs.device_cap_flags & IB_DEVICE_MEM_MGT_EXTENSIONS) {
newxprt->sc_frmr_pg_list_len =
dev->attrs.max_fast_reg_page_list_len;
newxprt->sc_dev_caps |= SVCRDMA_DEVCAP_FAST_REG;
newxprt->sc_reader = rdma_read_chunk_frmr;
} else
newxprt->sc_snd_w_inv = false;
......@@ -1056,7 +1052,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
sap = (struct sockaddr *)&newxprt->sc_cm_id->route.addr.dst_addr;
dprintk(" remote address : %pIS:%u\n", sap, rpc_get_port(sap));
dprintk(" max_sge : %d\n", newxprt->sc_max_sge);
dprintk(" max_sge_rd : %d\n", newxprt->sc_max_sge_rd);
dprintk(" sq_depth : %d\n", newxprt->sc_sq_depth);
dprintk(" max_requests : %d\n", newxprt->sc_max_requests);
dprintk(" ord : %d\n", newxprt->sc_ord);
......@@ -1117,12 +1112,6 @@ static void __svc_rdma_free(struct work_struct *work)
pr_err("svcrdma: sc_xprt still in use? (%d)\n",
kref_read(&xprt->xpt_ref));
/*
* Destroy queued, but not processed read completions. Note
* that this cleanup has to be done before destroying the
* cm_id because the device ptr is needed to unmap the dma in
* svc_rdma_put_context.
*/
while (!list_empty(&rdma->sc_read_complete_q)) {
struct svc_rdma_op_ctxt *ctxt;
ctxt = list_first_entry(&rdma->sc_read_complete_q,
......@@ -1130,8 +1119,6 @@ static void __svc_rdma_free(struct work_struct *work)
list_del(&ctxt->list);
svc_rdma_put_context(ctxt, 1);
}
/* Destroy queued, but not processed recv completions */
while (!list_empty(&rdma->sc_rq_dto_q)) {
struct svc_rdma_op_ctxt *ctxt;
ctxt = list_first_entry(&rdma->sc_rq_dto_q,
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7