public inbox for [email protected]
 help / color / mirror / Atom feed
From: Jonathan Lemon <[email protected]>
To: <[email protected]>
Cc: <[email protected]>
Subject: [RFC PATCH v2 03/13] io_uring: add register ifq opcode
Date: Tue, 18 Oct 2022 12:15:52 -0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

Add initial support for support for hooking in zero-copy interface
queues to io_uring.  This command requests a user-managed queue
from the specified network device.

This only includes the register opcode, unregistration is currently
done implicitly when the ring is removed.

Signed-off-by: Jonathan Lemon <[email protected]>
---
 include/uapi/linux/io_uring.h |  15 ++++
 io_uring/Makefile             |   3 +-
 io_uring/io_uring.c           |   8 +++
 io_uring/zctap.c              | 131 ++++++++++++++++++++++++++++++++++
 io_uring/zctap.h              |   9 +++
 5 files changed, 165 insertions(+), 1 deletion(-)
 create mode 100644 io_uring/zctap.c
 create mode 100644 io_uring/zctap.h

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ab7458033ee3..d406d21e8c38 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -490,6 +490,9 @@ enum {
 	/* register a range of fixed file slots for automatic slot allocation */
 	IORING_REGISTER_FILE_ALLOC_RANGE	= 25,
 
+	/* register a network ifq for zerocopy RX */
+	IORING_REGISTER_IFQ			= 26,
+
 	/* this goes last */
 	IORING_REGISTER_LAST
 };
@@ -666,6 +669,18 @@ struct io_uring_recvmsg_out {
 	__u32 flags;
 };
 
+/*
+ * Argument for IORING_REGISTER_IFQ
+ */
+struct io_uring_ifq_req {
+	__u32	ifindex;
+	__u16	queue_id;
+	__u16	ifq_id;
+	__u16	region_id;
+	__u16	fill_bgid;
+	__u16	__pad[2];
+};
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/io_uring/Makefile b/io_uring/Makefile
index 8cc8e5387a75..9d87e2e45ef9 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -7,5 +7,6 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o xattr.o nop.o fs.o splice.o \
 					openclose.o uring_cmd.o epoll.o \
 					statx.o net.o msg_ring.o timeout.o \
 					sqpoll.o fdinfo.o tctx.o poll.o \
-					cancel.o kbuf.o rsrc.o rw.o opdef.o notif.o
+					cancel.o kbuf.o rsrc.o rw.o opdef.o \
+					notif.o zctap.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 99a52f34b7d3..f6ac8db931ee 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -91,6 +91,7 @@
 #include "cancel.h"
 #include "net.h"
 #include "notif.h"
+#include "zctap.h"
 
 #include "timeout.h"
 #include "poll.h"
@@ -2809,6 +2810,7 @@ static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
 		__io_cqring_overflow_flush(ctx, true);
 	xa_for_each(&ctx->personalities, index, creds)
 		io_unregister_personality(ctx, index);
+	io_unregister_zctap_all(ctx);
 	if (ctx->rings)
 		io_poll_remove_all(ctx, NULL, true);
 	mutex_unlock(&ctx->uring_lock);
@@ -4033,6 +4035,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
 			break;
 		ret = io_register_file_alloc_range(ctx, arg);
 		break;
+	case IORING_REGISTER_IFQ:
+		ret = -EINVAL;
+		if (!arg || nr_args != 1)
+			break;
+		ret = io_register_ifq(ctx, arg);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
diff --git a/io_uring/zctap.c b/io_uring/zctap.c
new file mode 100644
index 000000000000..f4a45b683ca0
--- /dev/null
+++ b/io_uring/zctap.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/io_uring.h>
+#include <linux/netdevice.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "zctap.h"
+
+#define NR_ZCTAP_IFQS	1
+
+typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
+
+static int __io_queue_mgmt(struct net_device *dev, struct io_zctap_ifq *ifq,
+			   u16 queue_id)
+{
+	struct netdev_bpf cmd;
+	bpf_op_t ndo_bpf;
+
+	ndo_bpf = dev->netdev_ops->ndo_bpf;
+	if (!ndo_bpf)
+		return -EINVAL;
+
+	cmd.command = XDP_SETUP_ZCTAP;
+	cmd.zct.ifq = ifq;
+	cmd.zct.queue_id = queue_id;
+
+	return ndo_bpf(dev, &cmd);
+}
+
+static int io_open_zctap_ifq(struct io_zctap_ifq *ifq, u16 queue_id)
+{
+	return __io_queue_mgmt(ifq->dev, ifq, queue_id);
+}
+
+static int io_close_zctap_ifq(struct io_zctap_ifq *ifq, u16 queue_id)
+{
+	return __io_queue_mgmt(ifq->dev, NULL, queue_id);
+}
+
+static struct io_zctap_ifq *io_zctap_ifq_alloc(void)
+{
+	struct io_zctap_ifq *ifq;
+
+	ifq = kzalloc(sizeof(*ifq), GFP_KERNEL);
+	if (!ifq)
+		return NULL;
+
+	ifq->queue_id = -1;
+	return ifq;
+}
+
+static void io_zctap_ifq_free(struct io_zctap_ifq *ifq)
+{
+	if (ifq->queue_id != -1)
+		io_close_zctap_ifq(ifq, ifq->queue_id);
+	if (ifq->dev)
+		dev_put(ifq->dev);
+	kfree(ifq);
+}
+
+int io_register_ifq(struct io_ring_ctx *ctx,
+		    struct io_uring_ifq_req __user *arg)
+{
+	struct io_uring_ifq_req req;
+	struct io_zctap_ifq *ifq;
+	int err;
+
+	if (copy_from_user(&req, arg, sizeof(req)))
+		return -EFAULT;
+
+	if (req.ifq_id >= NR_ZCTAP_IFQS)
+		return -EFAULT;
+
+	if (ctx->zctap_ifq)
+		return -EBUSY;
+
+	ifq = io_zctap_ifq_alloc();
+	if (!ifq)
+		return -ENOMEM;
+
+	ifq->ctx = ctx;
+	ifq->fill_bgid = req.fill_bgid;
+
+	err = -ENODEV;
+	ifq->dev = dev_get_by_index(&init_net, req.ifindex);
+	if (!ifq->dev)
+		goto out;
+
+	/* region attachment TBD */
+
+	err = io_open_zctap_ifq(ifq, req.queue_id);
+	if (err)
+		goto out;
+	ifq->queue_id = req.queue_id;
+
+	ctx->zctap_ifq = ifq;
+
+	return 0;
+
+out:
+	io_zctap_ifq_free(ifq);
+	return err;
+}
+
+int io_unregister_zctap_ifq(struct io_ring_ctx *ctx, unsigned long index)
+{
+	struct io_zctap_ifq *ifq;
+
+	ifq = ctx->zctap_ifq;
+	if (!ifq)
+		return -EINVAL;
+
+	ctx->zctap_ifq = NULL;
+	io_zctap_ifq_free(ifq);
+
+	return 0;
+}
+
+void io_unregister_zctap_all(struct io_ring_ctx *ctx)
+{
+	int i;
+
+	for (i = 0; i < NR_ZCTAP_IFQS; i++)
+		io_unregister_zctap_ifq(ctx, i);
+}
diff --git a/io_uring/zctap.h b/io_uring/zctap.h
new file mode 100644
index 000000000000..bbe4a509408b
--- /dev/null
+++ b/io_uring/zctap.h
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_ZCTAP_H
+#define IOU_ZCTAP_H
+
+int io_register_ifq(struct io_ring_ctx *ctx,
+		    struct io_uring_ifq_req __user *arg);
+void io_unregister_zctap_all(struct io_ring_ctx *ctx);
+
+#endif
-- 
2.30.2


  parent reply	other threads:[~2022-10-18 19:16 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-18 19:15 [RFC PATCH v2 00/13] zero-copy RX for io_uring Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 01/13] io_uring: add zctap ifq definition Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 02/13] netdevice: add SETUP_ZCTAP to the netdev_bpf structure Jonathan Lemon
2022-10-18 19:15 ` Jonathan Lemon [this message]
2022-10-18 19:15 ` [RFC PATCH v2 04/13] io_uring: create a zctap region for a mapped buffer Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 05/13] io_uring: create page freelist for the ifq region Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 06/13] io_uring: Provide driver API for zctap packet buffers Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 07/13] io_uring: Allocate the zctap buffers for the device Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 08/13] io_uring: Add zctap buffer get/put functions and refcounting Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 09/13] skbuff: Introduce SKBFL_FIXED_FRAG and skb_fixed() Jonathan Lemon
2022-10-18 19:15 ` [RFC PATCH v2 10/13] io_uring: Allocate a uarg for use by the ifq RX Jonathan Lemon
2022-10-18 19:16 ` [RFC PATCH v2 11/13] io_uring: Define the zctap iov[] returned to the user Jonathan Lemon
2022-10-18 19:16 ` [RFC PATCH v2 12/13] io_uring: add OP_RECV_ZC command Jonathan Lemon
2022-10-18 19:16 ` [RFC PATCH v2 13/13] io_uring: Make remove_ifq_region a delayed work call Jonathan Lemon
2022-10-20  3:35 ` [RFC PATCH v2 00/13] zero-copy RX for io_uring Ziyang Zhang
2022-11-02 23:33   ` Jonathan Lemon

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 \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /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