summaryrefslogtreecommitdiffstats
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-01-11 11:35:46 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2021-01-11 11:35:46 -0800
commitc912fd05fab97934e4cf579654d0dc4835b4758c (patch)
tree2347f7c161893f46c78f2bbe4f7f9d7458b5c2f3 /net
parentf1ee3e150bd9da2dd60a210926c86cffd4a336ea (diff)
parent7b723008f9c95624c848fad661c01b06e47b20da (diff)
downloadlinux-stable-c912fd05fab97934e4cf579654d0dc4835b4758c.tar.gz
linux-stable-c912fd05fab97934e4cf579654d0dc4835b4758c.tar.bz2
linux-stable-c912fd05fab97934e4cf579654d0dc4835b4758c.zip
Merge tag 'nfsd-5.11-1' of git://git.linux-nfs.org/projects/cel/cel-2.6
Pull nfsd fixes from Chuck Lever: - Fix major TCP performance regression - Get NFSv4.2 READ_PLUS regression tests to pass - Improve NFSv4 COMPOUND memory allocation - Fix sparse warning * tag 'nfsd-5.11-1' of git://git.linux-nfs.org/projects/cel/cel-2.6: NFSD: Restore NFSv4 decoding's SAVEMEM functionality SUNRPC: Handle TCP socket sends with kernel_sendpage() again NFSD: Fix sparse warning in nfssvc.c nfsd: Don't set eof on a truncated READ_PLUS nfsd: Fixes for nfsd4_encode_read_plus_data()
Diffstat (limited to 'net')
-rw-r--r--net/sunrpc/svcsock.c86
1 files changed, 85 insertions, 1 deletions
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index b248f2349437..c9766d07eb81 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1062,6 +1062,90 @@ err_noclose:
return 0; /* record not complete */
}
+static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
+ int flags)
+{
+ return kernel_sendpage(sock, virt_to_page(vec->iov_base),
+ offset_in_page(vec->iov_base),
+ vec->iov_len, flags);
+}
+
+/*
+ * kernel_sendpage() is used exclusively to reduce the number of
+ * copy operations in this path. Therefore the caller must ensure
+ * that the pages backing @xdr are unchanging.
+ *
+ * In addition, the logic assumes that * .bv_len is never larger
+ * than PAGE_SIZE.
+ */
+static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
+ struct xdr_buf *xdr, rpc_fraghdr marker,
+ unsigned int *sentp)
+{
+ const struct kvec *head = xdr->head;
+ const struct kvec *tail = xdr->tail;
+ struct kvec rm = {
+ .iov_base = &marker,
+ .iov_len = sizeof(marker),
+ };
+ int flags, ret;
+
+ *sentp = 0;
+ xdr_alloc_bvec(xdr, GFP_KERNEL);
+
+ msg->msg_flags = MSG_MORE;
+ ret = kernel_sendmsg(sock, msg, &rm, 1, rm.iov_len);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ if (ret != rm.iov_len)
+ return -EAGAIN;
+
+ flags = head->iov_len < xdr->len ? MSG_MORE | MSG_SENDPAGE_NOTLAST : 0;
+ ret = svc_tcp_send_kvec(sock, head, flags);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ if (ret != head->iov_len)
+ goto out;
+
+ if (xdr->page_len) {
+ unsigned int offset, len, remaining;
+ struct bio_vec *bvec;
+
+ bvec = xdr->bvec;
+ offset = xdr->page_base;
+ remaining = xdr->page_len;
+ flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+ while (remaining > 0) {
+ if (remaining <= PAGE_SIZE && tail->iov_len == 0)
+ flags = 0;
+ len = min(remaining, bvec->bv_len);
+ ret = kernel_sendpage(sock, bvec->bv_page,
+ bvec->bv_offset + offset,
+ len, flags);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ if (ret != len)
+ goto out;
+ remaining -= len;
+ offset = 0;
+ bvec++;
+ }
+ }
+
+ if (tail->iov_len) {
+ ret = svc_tcp_send_kvec(sock, tail, 0);
+ if (ret < 0)
+ return ret;
+ *sentp += ret;
+ }
+
+out:
+ return 0;
+}
+
/**
* svc_tcp_sendto - Send out a reply on a TCP socket
* @rqstp: completed svc_rqst
@@ -1089,7 +1173,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
mutex_lock(&xprt->xpt_mutex);
if (svc_xprt_is_dead(xprt))
goto out_notconn;
- err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent);
+ err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent);
xdr_free_bvec(xdr);
trace_svcsock_tcp_send(xprt, err < 0 ? err : sent);
if (err < 0 || sent != (xdr->len + sizeof(marker)))