summaryrefslogtreecommitdiff
path: root/net/smc/smc_rx.c
diff options
context:
space:
mode:
authorStefan Raspl <stefan.raspl@linux.ibm.com>2018-05-03 19:12:39 +0300
committerDavid S. Miller <davem@davemloft.net>2018-05-04 18:45:06 +0300
commit9014db202cb764b8e14c53e7bacc81f9a1a2ba7f (patch)
tree2beb8b962fd2261b7f7d372d8e463777234fa7fc /net/smc/smc_rx.c
parent2ef4f27ad00dc9d36cadb81fce9d07366d579451 (diff)
downloadlinux-9014db202cb764b8e14c53e7bacc81f9a1a2ba7f.tar.xz
smc: add support for splice()
Provide an implementation for splice() when we are using SMC. See smc_splice_read() for further details. Signed-off-by: Stefan Raspl <raspl@linux.ibm.com> Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>< Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/smc/smc_rx.c')
-rw-r--r--net/smc/smc_rx.c163
1 files changed, 147 insertions, 16 deletions
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 7b64bee656e8..ed45569289f5 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -43,6 +43,116 @@ static void smc_rx_wake_up(struct sock *sk)
rcu_read_unlock();
}
+/* Update consumer cursor
+ * @conn connection to update
+ * @cons consumer cursor
+ * @len number of Bytes consumed
+ */
+static void smc_rx_update_consumer(struct smc_connection *conn,
+ union smc_host_cursor cons, size_t len)
+{
+ smc_curs_add(conn->rmbe_size, &cons, len);
+ smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn),
+ conn);
+ /* send consumer cursor update if required */
+ /* similar to advertising new TCP rcv_wnd if required */
+ smc_tx_consumer_update(conn);
+}
+
+struct smc_spd_priv {
+ struct smc_sock *smc;
+ size_t len;
+};
+
+static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private;
+ struct smc_sock *smc = priv->smc;
+ struct smc_connection *conn;
+ union smc_host_cursor cons;
+ struct sock *sk = &smc->sk;
+
+ if (sk->sk_state == SMC_CLOSED ||
+ sk->sk_state == SMC_PEERFINCLOSEWAIT ||
+ sk->sk_state == SMC_APPFINCLOSEWAIT)
+ goto out;
+ conn = &smc->conn;
+ lock_sock(sk);
+ smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn),
+ conn);
+ smc_rx_update_consumer(conn, cons, priv->len);
+ release_sock(sk);
+ if (atomic_sub_and_test(priv->len, &conn->splice_pending))
+ smc_rx_wake_up(sk);
+out:
+ kfree(priv);
+ put_page(buf->page);
+ sock_put(sk);
+}
+
+static int smc_rx_pipe_buf_nosteal(struct pipe_inode_info *pipe,
+ struct pipe_buffer *buf)
+{
+ return 1;
+}
+
+static const struct pipe_buf_operations smc_pipe_ops = {
+ .can_merge = 0,
+ .confirm = generic_pipe_buf_confirm,
+ .release = smc_rx_pipe_buf_release,
+ .steal = smc_rx_pipe_buf_nosteal,
+ .get = generic_pipe_buf_get
+};
+
+static void smc_rx_spd_release(struct splice_pipe_desc *spd,
+ unsigned int i)
+{
+ put_page(spd->pages[i]);
+}
+
+static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
+ struct smc_sock *smc)
+{
+ struct splice_pipe_desc spd;
+ struct partial_page partial;
+ struct smc_spd_priv *priv;
+ struct page *page;
+ int bytes;
+
+ page = virt_to_page(smc->conn.rmb_desc->cpu_addr);
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+ priv->len = len;
+ priv->smc = smc;
+ partial.offset = src - (char *)smc->conn.rmb_desc->cpu_addr;
+ partial.len = len;
+ partial.private = (unsigned long)priv;
+
+ spd.nr_pages_max = 1;
+ spd.nr_pages = 1;
+ spd.pages = &page;
+ spd.partial = &partial;
+ spd.ops = &smc_pipe_ops;
+ spd.spd_release = smc_rx_spd_release;
+
+ bytes = splice_to_pipe(pipe, &spd);
+ if (bytes > 0) {
+ sock_hold(&smc->sk);
+ get_page(smc->conn.rmb_desc->pages);
+ atomic_add(bytes, &smc->conn.splice_pending);
+ }
+
+ return bytes;
+}
+
+static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn)
+{
+ return atomic_read(&conn->bytes_to_rcv) &&
+ !atomic_read(&conn->splice_pending);
+}
+
/* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted
* @smc smc socket
* @timeo pointer to max seconds to wait, pointer to value 0 for no timeout
@@ -74,19 +184,25 @@ int smc_rx_wait(struct smc_sock *smc, long *timeo,
return rc;
}
-/* rcvbuf consumer: main API called by socket layer.
- * called under sk lock.
+/* smc_rx_recvmsg - receive data from RMBE
+ * @msg: copy data to receive buffer
+ * @pipe: copy data to pipe if set - indicates splice() call
+ *
+ * rcvbuf consumer: main API called by socket layer.
+ * Called under sk lock.
*/
-int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
- int flags)
+int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
+ struct pipe_inode_info *pipe, size_t len, int flags)
{
size_t copylen, read_done = 0, read_remaining = len;
size_t chunk_len, chunk_off, chunk_len_sum;
struct smc_connection *conn = &smc->conn;
+ int (*func)(struct smc_connection *conn);
union smc_host_cursor cons;
int readable, chunk;
char *rcvbuf_base;
struct sock *sk;
+ int splbytes;
long timeo;
int target; /* Read at least these many bytes */
int rc;
@@ -102,12 +218,11 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len,
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
- msg->msg_namelen = 0;
/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
rcvbuf_base = conn->rmb_desc->cpu_addr;
do { /* while (read_remaining) */
- if (read_done >= target)
+ if (read_done >= target || (pipe && read_done))
break;
if (atomic_read(&conn->bytes_to_rcv))
@@ -156,11 +271,24 @@ copy:
/* initialize variables for 1st iteration of subsequent loop */
/* could be just 1 byte, even after waiting on data above */
readable = atomic_read(&conn->bytes_to_rcv);
+ splbytes = atomic_read(&conn->splice_pending);
+ if (!readable || (msg && splbytes)) {
+ if (splbytes)
+ func = smc_rx_data_available_and_no_splice_pend;
+ else
+ func = smc_rx_data_available;
+ smc_rx_wait(smc, &timeo, func);
+ continue;
+ }
+
/* not more than what user space asked for */
copylen = min_t(size_t, read_remaining, readable);
smc_curs_write(&cons,
smc_curs_read(&conn->local_tx_ctrl.cons, conn),
conn);
+ /* subsequent splice() calls pick up where previous left */
+ if (splbytes)
+ smc_curs_add(conn->rmbe_size, &cons, splbytes);
/* determine chunks where to read from rcvbuf */
/* either unwrapped case, or 1st chunk of wrapped case */
chunk_len = min_t(size_t,
@@ -170,9 +298,16 @@ copy:
smc_rmb_sync_sg_for_cpu(conn);
for (chunk = 0; chunk < 2; chunk++) {
if (!(flags & MSG_TRUNC)) {
- rc = memcpy_to_msg(msg, rcvbuf_base + chunk_off,
- chunk_len);
- if (rc) {
+ if (msg) {
+ rc = memcpy_to_msg(msg, rcvbuf_base +
+ chunk_off,
+ chunk_len);
+ } else {
+ rc = smc_rx_splice(pipe, rcvbuf_base +
+ chunk_off, chunk_len,
+ smc);
+ }
+ if (rc < 0) {
if (!read_done)
read_done = -EFAULT;
smc_rmb_sync_sg_for_device(conn);
@@ -193,18 +328,13 @@ copy:
/* update cursors */
if (!(flags & MSG_PEEK)) {
- smc_curs_add(conn->rmbe_size, &cons, copylen);
/* increased in recv tasklet smc_cdc_msg_rcv() */
smp_mb__before_atomic();
atomic_sub(copylen, &conn->bytes_to_rcv);
/* guarantee 0 <= bytes_to_rcv <= rmbe_size */
smp_mb__after_atomic();
- smc_curs_write(&conn->local_tx_ctrl.cons,
- smc_curs_read(&cons, conn),
- conn);
- /* send consumer cursor update if required */
- /* similar to advertising new TCP rcv_wnd if required */
- smc_tx_consumer_update(conn);
+ if (msg)
+ smc_rx_update_consumer(conn, cons, copylen);
}
} while (read_remaining);
out:
@@ -215,4 +345,5 @@ out:
void smc_rx_init(struct smc_sock *smc)
{
smc->sk.sk_data_ready = smc_rx_wake_up;
+ atomic_set(&smc->conn.splice_pending, 0);
}