From: David Wei <dw@davidwei.uk>
To: io-uring@vger.kernel.org, netdev@vger.kernel.org
Cc: Jens Axboe <axboe@kernel.dk>,
Pavel Begunkov <asml.silence@gmail.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jesper Dangaard Brouer <hawk@kernel.org>,
David Ahern <dsahern@kernel.org>,
Mina Almasry <almasrymina@google.com>
Subject: [RFC PATCH v4 09/16] io_uring/zcrx: implement socket registration
Date: Tue, 12 Mar 2024 14:44:23 -0700 [thread overview]
Message-ID: <20240312214430.2923019-10-dw@davidwei.uk> (raw)
In-Reply-To: <20240312214430.2923019-1-dw@davidwei.uk>
From: Pavel Begunkov <asml.silence@gmail.com>
We want userspace to explicitly list all sockets it'll be using with a
particular zc ifq, so we can properly configure them, e.g. binding the
sockets to the corresponding interface and setting steering rules. We'll
also need it to better control ifq lifetime and for
termination / unregistration purposes.
TODO: remove zc_rx_idx from struct socket, which will fix zc_rx_idx
token init races and re-registration bug.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
---
include/linux/net.h | 2 +
include/uapi/linux/io_uring.h | 7 +++
io_uring/net.c | 20 ++++++++
io_uring/register.c | 6 +++
io_uring/zc_rx.c | 91 +++++++++++++++++++++++++++++++++--
io_uring/zc_rx.h | 17 +++++++
net/socket.c | 1 +
7 files changed, 141 insertions(+), 3 deletions(-)
diff --git a/include/linux/net.h b/include/linux/net.h
index c9b4a63791a4..867061a91d30 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -126,6 +126,8 @@ struct socket {
const struct proto_ops *ops; /* Might change with IPV6_ADDRFORM or MPTCP. */
struct socket_wq wq;
+
+ unsigned zc_rx_idx;
};
/*
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index a085ed60478f..26e945e6258d 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -579,6 +579,7 @@ enum {
/* register a network interface queue for zerocopy */
IORING_REGISTER_ZC_RX_IFQ = 29,
+ IORING_REGISTER_ZC_RX_SOCK = 30,
/* this goes last */
IORING_REGISTER_LAST,
@@ -824,6 +825,12 @@ struct io_uring_zc_rx_ifq_reg {
struct io_rbuf_rqring_offsets rq_off;
};
+struct io_uring_zc_rx_sock_reg {
+ __u32 sockfd;
+ __u32 zc_rx_ifq_idx;
+ __u32 __resv[2];
+};
+
#ifdef __cplusplus
}
#endif
diff --git a/io_uring/net.c b/io_uring/net.c
index 54dff492e064..1fa7c1fa6b5d 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -16,6 +16,7 @@
#include "net.h"
#include "notif.h"
#include "rsrc.h"
+#include "zc_rx.h"
#if defined(CONFIG_NET)
struct io_shutdown {
@@ -1033,6 +1034,25 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
return ret;
}
+static __maybe_unused
+struct io_zc_rx_ifq *io_zc_verify_sock(struct io_kiocb *req,
+ struct socket *sock)
+{
+ unsigned token = READ_ONCE(sock->zc_rx_idx);
+ unsigned ifq_idx = token >> IO_ZC_IFQ_IDX_OFFSET;
+ unsigned sock_idx = token & IO_ZC_IFQ_IDX_MASK;
+ struct io_zc_rx_ifq *ifq;
+
+ if (ifq_idx)
+ return NULL;
+ ifq = req->ctx->ifq;
+ if (!ifq || sock_idx >= ifq->nr_sockets)
+ return NULL;
+ if (ifq->sockets[sock_idx] != req->file)
+ return NULL;
+ return ifq;
+}
+
void io_send_zc_cleanup(struct io_kiocb *req)
{
struct io_sr_msg *zc = io_kiocb_to_cmd(req, struct io_sr_msg);
diff --git a/io_uring/register.c b/io_uring/register.c
index 760f0b6a051c..7f40403a1716 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -570,6 +570,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
break;
ret = io_register_zc_rx_ifq(ctx, arg);
break;
+ case IORING_REGISTER_ZC_RX_SOCK:
+ ret = -EINVAL;
+ if (!arg || nr_args != 1)
+ break;
+ ret = io_register_zc_rx_sock(ctx, arg);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/io_uring/zc_rx.c b/io_uring/zc_rx.c
index 521eeea04f9d..77459c0fc14b 100644
--- a/io_uring/zc_rx.c
+++ b/io_uring/zc_rx.c
@@ -5,12 +5,15 @@
#include <linux/mm.h>
#include <linux/io_uring.h>
#include <linux/netdevice.h>
+#include <net/tcp.h>
+#include <net/af_unix.h>
#include <uapi/linux/io_uring.h>
#include "io_uring.h"
#include "kbuf.h"
#include "zc_rx.h"
+#include "rsrc.h"
typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
@@ -76,10 +79,31 @@ static struct io_zc_rx_ifq *io_zc_rx_ifq_alloc(struct io_ring_ctx *ctx)
return ifq;
}
-static void io_zc_rx_ifq_free(struct io_zc_rx_ifq *ifq)
+static void io_shutdown_ifq(struct io_zc_rx_ifq *ifq)
{
- if (ifq->if_rxq_id != -1)
+ int i;
+
+ if (!ifq)
+ return;
+
+ for (i = 0; i < ifq->nr_sockets; i++) {
+ if (ifq->sockets[i]) {
+ fput(ifq->sockets[i]);
+ ifq->sockets[i] = NULL;
+ }
+ }
+ ifq->nr_sockets = 0;
+
+ if (ifq->if_rxq_id != -1) {
io_close_zc_rxq(ifq);
+ ifq->if_rxq_id = -1;
+ }
+}
+
+static void io_zc_rx_ifq_free(struct io_zc_rx_ifq *ifq)
+{
+ io_shutdown_ifq(ifq);
+
if (ifq->dev)
dev_put(ifq->dev);
io_free_rbuf_ring(ifq);
@@ -132,7 +156,6 @@ int io_register_zc_rx_ifq(struct io_ring_ctx *ctx,
reg.rq_off.tail = offsetof(struct io_uring, tail);
if (copy_to_user(arg, ®, sizeof(reg))) {
- io_close_zc_rxq(ifq);
ret = -EFAULT;
goto err;
}
@@ -153,6 +176,8 @@ void io_unregister_zc_rx_ifqs(struct io_ring_ctx *ctx)
if (!ifq)
return;
+ WARN_ON_ONCE(ifq->nr_sockets);
+
ctx->ifq = NULL;
io_zc_rx_ifq_free(ifq);
}
@@ -160,6 +185,66 @@ void io_unregister_zc_rx_ifqs(struct io_ring_ctx *ctx)
void io_shutdown_zc_rx_ifqs(struct io_ring_ctx *ctx)
{
lockdep_assert_held(&ctx->uring_lock);
+
+ io_shutdown_ifq(ctx->ifq);
+}
+
+int io_register_zc_rx_sock(struct io_ring_ctx *ctx,
+ struct io_uring_zc_rx_sock_reg __user *arg)
+{
+ struct io_uring_zc_rx_sock_reg sr;
+ struct io_zc_rx_ifq *ifq;
+ struct socket *sock;
+ struct file *file;
+ int ret = -EEXIST;
+ int idx;
+
+ if (copy_from_user(&sr, arg, sizeof(sr)))
+ return -EFAULT;
+ if (sr.__resv[0] || sr.__resv[1])
+ return -EINVAL;
+ if (sr.zc_rx_ifq_idx != 0 || !ctx->ifq)
+ return -EINVAL;
+
+ ifq = ctx->ifq;
+ if (ifq->nr_sockets >= ARRAY_SIZE(ifq->sockets))
+ return -EINVAL;
+
+ BUILD_BUG_ON(ARRAY_SIZE(ifq->sockets) > IO_ZC_IFQ_IDX_MASK);
+
+ file = fget(sr.sockfd);
+ if (!file)
+ return -EBADF;
+
+ if (!!unix_get_socket(file)) {
+ fput(file);
+ return -EBADF;
+ }
+
+ sock = sock_from_file(file);
+ if (unlikely(!sock || !sock->sk)) {
+ fput(file);
+ return -ENOTSOCK;
+ }
+
+ idx = ifq->nr_sockets;
+ lock_sock(sock->sk);
+ if (!sock->zc_rx_idx) {
+ unsigned token;
+
+ token = idx + (sr.zc_rx_ifq_idx << IO_ZC_IFQ_IDX_OFFSET);
+ WRITE_ONCE(sock->zc_rx_idx, token);
+ ret = 0;
+ }
+ release_sock(sock->sk);
+
+ if (ret) {
+ fput(file);
+ return ret;
+ }
+ ifq->sockets[idx] = file;
+ ifq->nr_sockets++;
+ return 0;
}
#endif
diff --git a/io_uring/zc_rx.h b/io_uring/zc_rx.h
index 35b019b275e0..d7b8397d525f 100644
--- a/io_uring/zc_rx.h
+++ b/io_uring/zc_rx.h
@@ -2,6 +2,13 @@
#ifndef IOU_ZC_RX_H
#define IOU_ZC_RX_H
+#include <linux/io_uring_types.h>
+#include <linux/skbuff.h>
+
+#define IO_ZC_MAX_IFQ_SOCKETS 16
+#define IO_ZC_IFQ_IDX_OFFSET 16
+#define IO_ZC_IFQ_IDX_MASK ((1U << IO_ZC_IFQ_IDX_OFFSET) - 1)
+
struct io_zc_rx_ifq {
struct io_ring_ctx *ctx;
struct net_device *dev;
@@ -11,6 +18,9 @@ struct io_zc_rx_ifq {
/* hw rx descriptor ring id */
u32 if_rxq_id;
+
+ unsigned nr_sockets;
+ struct file *sockets[IO_ZC_MAX_IFQ_SOCKETS];
};
#if defined(CONFIG_PAGE_POOL)
@@ -18,6 +28,8 @@ int io_register_zc_rx_ifq(struct io_ring_ctx *ctx,
struct io_uring_zc_rx_ifq_reg __user *arg);
void io_unregister_zc_rx_ifqs(struct io_ring_ctx *ctx);
void io_shutdown_zc_rx_ifqs(struct io_ring_ctx *ctx);
+int io_register_zc_rx_sock(struct io_ring_ctx *ctx,
+ struct io_uring_zc_rx_sock_reg __user *arg);
#else
static inline int io_register_zc_rx_ifq(struct io_ring_ctx *ctx,
struct io_uring_zc_rx_ifq_reg __user *arg)
@@ -30,6 +42,11 @@ static inline void io_unregister_zc_rx_ifqs(struct io_ring_ctx *ctx)
static inline void io_shutdown_zc_rx_ifqs(struct io_ring_ctx *ctx)
{
}
+static inline int io_register_zc_rx_sock(struct io_ring_ctx *ctx,
+ struct io_uring_zc_rx_sock_reg __user *arg)
+{
+ return -EOPNOTSUPP;
+}
#endif
#endif
diff --git a/net/socket.c b/net/socket.c
index c69cd0e652b8..18181a4e0295 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -637,6 +637,7 @@ struct socket *sock_alloc(void)
sock = SOCKET_I(inode);
+ sock->zc_rx_idx = 0;
inode->i_ino = get_next_ino();
inode->i_mode = S_IFSOCK | S_IRWXUGO;
inode->i_uid = current_fsuid();
--
2.43.0
next prev parent reply other threads:[~2024-03-12 21:44 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-03-12 21:44 [RFC PATCH v4 00/16] Zero copy Rx using io_uring David Wei
2024-03-12 21:44 ` [RFC PATCH v4 01/16] net: generalise pp provider params passing David Wei
2024-03-12 21:44 ` [RFC PATCH v4 02/16] io_uring: delayed cqe commit David Wei
2024-03-12 21:44 ` [RFC PATCH v4 03/16] net: page_pool: add ->scrub mem provider callback David Wei
2024-03-12 21:44 ` [RFC PATCH v4 04/16] io_uring: separate header for exported net bits David Wei
2024-03-12 21:44 ` [RFC PATCH v4 05/16] io_uring: introduce interface queue David Wei
2024-03-12 21:44 ` [RFC PATCH v4 06/16] io_uring: add mmap support for shared ifq ringbuffers David Wei
2024-03-12 21:44 ` [RFC PATCH v4 07/16] netdev: add XDP_SETUP_ZC_RX command David Wei
2024-03-12 21:44 ` [RFC PATCH v4 08/16] io_uring: setup ZC for an Rx queue when registering an ifq David Wei
2024-03-12 21:44 ` David Wei [this message]
2024-03-12 21:44 ` [RFC PATCH v4 10/16] io_uring: add zero copy buf representation and pool David Wei
2024-03-12 21:44 ` [RFC PATCH v4 11/16] io_uring: implement pp memory provider for zc rx David Wei
2024-03-12 21:44 ` [RFC PATCH v4 12/16] io_uring/zcrx: implement PP_FLAG_DMA_* handling David Wei
2024-03-12 21:44 ` [RFC PATCH v4 13/16] io_uring: add io_recvzc request David Wei
2024-03-13 20:25 ` Jens Axboe
2024-03-13 20:26 ` Pavel Begunkov
2024-03-13 21:03 ` Jens Axboe
2024-03-14 16:14 ` Jens Axboe
2024-03-15 17:34 ` Pavel Begunkov
2024-03-15 18:38 ` Jens Axboe
2024-03-15 23:52 ` Pavel Begunkov
2024-03-16 16:59 ` Jens Axboe
2024-03-17 21:22 ` Pavel Begunkov
2024-03-17 21:30 ` Jens Axboe
2024-03-12 21:44 ` [RFC PATCH v4 14/16] net: execute custom callback from napi David Wei
2024-03-12 21:44 ` [RFC PATCH v4 15/16] io_uring/zcrx: add copy fallback David Wei
2024-03-12 21:44 ` [RFC PATCH v4 16/16] veth: add support for io_uring zc rx David Wei
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240312214430.2923019-10-dw@davidwei.uk \
--to=dw@davidwei.uk \
--cc=almasrymina@google.com \
--cc=asml.silence@gmail.com \
--cc=axboe@kernel.dk \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=hawk@kernel.org \
--cc=io-uring@vger.kernel.org \
--cc=kuba@kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox