From: David Wei <[email protected]>
To: [email protected], [email protected]
Cc: Jens Axboe <[email protected]>,
Pavel Begunkov <[email protected]>,
Jakub Kicinski <[email protected]>, Paolo Abeni <[email protected]>,
"David S. Miller" <[email protected]>,
Eric Dumazet <[email protected]>,
Jesper Dangaard Brouer <[email protected]>,
David Ahern <[email protected]>,
Mina Almasry <[email protected]>,
Stanislav Fomichev <[email protected]>,
Joe Damato <[email protected]>,
Pedro Tammela <[email protected]>
Subject: [PATCH v7 09/15] io_uring/zcrx: add interface queue and refill queue
Date: Tue, 29 Oct 2024 16:05:12 -0700 [thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>
From: David Wei <[email protected]>
Add a new object called an interface queue (ifq) that represents a net
rx queue that has been configured for zero copy. Each ifq is registered
using a new registration opcode IORING_REGISTER_ZCRX_IFQ.
The refill queue is allocated by the kernel and mapped by userspace
using a new offset IORING_OFF_RQ_RING, in a similar fashion to the main
SQ/CQ. It is used by userspace to return buffers that it is done with,
which will then be re-used by the netdev again.
The main CQ ring is used to notify userspace of received data by using
the upper 16 bytes of a big CQE as a new struct io_uring_zcrx_cqe. Each
entry contains the offset + len to the data.
For now, each io_uring instance only has a single ifq.
Signed-off-by: David Wei <[email protected]>
---
Kconfig | 2 +
include/linux/io_uring_types.h | 3 +
include/uapi/linux/io_uring.h | 43 ++++++++++
io_uring/KConfig | 10 +++
io_uring/Makefile | 1 +
io_uring/io_uring.c | 7 ++
io_uring/memmap.c | 8 ++
io_uring/register.c | 7 ++
io_uring/zcrx.c | 143 +++++++++++++++++++++++++++++++++
io_uring/zcrx.h | 39 +++++++++
10 files changed, 263 insertions(+)
create mode 100644 io_uring/KConfig
create mode 100644 io_uring/zcrx.c
create mode 100644 io_uring/zcrx.h
diff --git a/Kconfig b/Kconfig
index 745bc773f567..529ea7694ba9 100644
--- a/Kconfig
+++ b/Kconfig
@@ -30,3 +30,5 @@ source "lib/Kconfig"
source "lib/Kconfig.debug"
source "Documentation/Kconfig"
+
+source "io_uring/KConfig"
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 6d3ee71bd832..f0f6d3d186b1 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -39,6 +39,8 @@ enum io_uring_cmd_flags {
IO_URING_F_COMPAT = (1 << 12),
};
+struct io_zcrx_ifq;
+
struct io_wq_work_node {
struct io_wq_work_node *next;
};
@@ -373,6 +375,7 @@ struct io_ring_ctx {
struct io_alloc_cache rsrc_node_cache;
struct wait_queue_head rsrc_quiesce_wq;
unsigned rsrc_quiesce;
+ struct io_zcrx_ifq *ifq;
u32 pers_next;
struct xarray personalities;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 86cb385fe0b5..d398e19f8eea 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -467,6 +467,8 @@ struct io_uring_cqe {
#define IORING_OFF_PBUF_RING 0x80000000ULL
#define IORING_OFF_PBUF_SHIFT 16
#define IORING_OFF_MMAP_MASK 0xf8000000ULL
+#define IORING_OFF_RQ_RING 0x20000000ULL
+#define IORING_OFF_RQ_SHIFT 16
/*
* Filled with the offset for mmap(2)
@@ -615,6 +617,9 @@ enum io_uring_register_op {
/* send MSG_RING without having a ring */
IORING_REGISTER_SEND_MSG_RING = 31,
+ /* register a netdev hw rx queue for zerocopy */
+ IORING_REGISTER_ZCRX_IFQ = 32,
+
/* this goes last */
IORING_REGISTER_LAST,
@@ -845,6 +850,44 @@ enum io_uring_socket_op {
SOCKET_URING_OP_SETSOCKOPT,
};
+/* Zero copy receive refill queue entry */
+struct io_uring_zcrx_rqe {
+ __u64 off;
+ __u32 len;
+ __u32 __pad;
+};
+
+struct io_uring_zcrx_cqe {
+ __u64 off;
+ __u64 __pad;
+};
+
+/* The bit from which area id is encoded into offsets */
+#define IORING_ZCRX_AREA_SHIFT 48
+#define IORING_ZCRX_AREA_MASK (~(((__u64)1 << IORING_ZCRX_AREA_SHIFT) - 1))
+
+struct io_uring_zcrx_offsets {
+ __u32 head;
+ __u32 tail;
+ __u32 rqes;
+ __u32 mmap_sz;
+ __u64 __resv[2];
+};
+
+/*
+ * Argument for IORING_REGISTER_ZCRX_IFQ
+ */
+struct io_uring_zcrx_ifq_reg {
+ __u32 if_idx;
+ __u32 if_rxq;
+ __u32 rq_entries;
+ __u32 flags;
+
+ __u64 area_ptr; /* pointer to struct io_uring_zcrx_area_reg */
+ struct io_uring_zcrx_offsets offsets;
+ __u64 __resv[3];
+};
+
#ifdef __cplusplus
}
#endif
diff --git a/io_uring/KConfig b/io_uring/KConfig
new file mode 100644
index 000000000000..9e2a4beba1ef
--- /dev/null
+++ b/io_uring/KConfig
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# io_uring configuration
+#
+
+config IO_URING_ZCRX
+ def_bool y
+ depends on PAGE_POOL
+ depends on INET
+ depends on NET_RX_BUSY_POLL
diff --git a/io_uring/Makefile b/io_uring/Makefile
index 53167bef37d7..a95b0b8229c9 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_IO_URING) += io_uring.o opdef.o kbuf.o rsrc.o notif.o \
epoll.o statx.o timeout.o fdinfo.o \
cancel.o waitid.o register.o \
truncate.o memmap.o
+obj-$(CONFIG_IO_URING_ZCRX) += zcrx.o
obj-$(CONFIG_IO_WQ) += io-wq.o
obj-$(CONFIG_FUTEX) += futex.o
obj-$(CONFIG_NET_RX_BUSY_POLL) += napi.o
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 58b401900b41..49d73c793f06 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -98,6 +98,7 @@
#include "uring_cmd.h"
#include "msg_ring.h"
#include "memmap.h"
+#include "zcrx.h"
#include "timeout.h"
#include "poll.h"
@@ -2729,6 +2730,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
return;
mutex_lock(&ctx->uring_lock);
+ io_unregister_zcrx_ifqs(ctx);
if (ctx->buf_data)
__io_sqe_buffers_unregister(ctx);
if (ctx->file_data)
@@ -2903,6 +2905,11 @@ static __cold void io_ring_exit_work(struct work_struct *work)
io_cqring_overflow_kill(ctx);
mutex_unlock(&ctx->uring_lock);
}
+ if (ctx->ifq) {
+ mutex_lock(&ctx->uring_lock);
+ io_shutdown_zcrx_ifqs(ctx);
+ mutex_unlock(&ctx->uring_lock);
+ }
if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
io_move_task_work_from_local(ctx);
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index a0f32a255fd1..4c384e8615f6 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -12,6 +12,7 @@
#include "memmap.h"
#include "kbuf.h"
+#include "zcrx.h"
static void *io_mem_alloc_compound(struct page **pages, int nr_pages,
size_t size, gfp_t gfp)
@@ -223,6 +224,10 @@ static void *io_uring_validate_mmap_request(struct file *file, loff_t pgoff,
io_put_bl(ctx, bl);
return ptr;
}
+ case IORING_OFF_RQ_RING:
+ if (!ctx->ifq)
+ return ERR_PTR(-EINVAL);
+ return ctx->ifq->rq_ring;
}
return ERR_PTR(-EINVAL);
@@ -261,6 +266,9 @@ __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
ctx->n_sqe_pages);
case IORING_OFF_PBUF_RING:
return io_pbuf_mmap(file, vma);
+ case IORING_OFF_RQ_RING:
+ return io_uring_mmap_pages(ctx, vma, ctx->ifq->rqe_pages,
+ ctx->ifq->n_rqe_pages);
}
return -EINVAL;
diff --git a/io_uring/register.c b/io_uring/register.c
index 52b2f9b74af8..1fac52b14e3d 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -29,6 +29,7 @@
#include "napi.h"
#include "eventfd.h"
#include "msg_ring.h"
+#include "zcrx.h"
#define IORING_MAX_RESTRICTIONS (IORING_RESTRICTION_LAST + \
IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -549,6 +550,12 @@ static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
break;
ret = io_register_clone_buffers(ctx, arg);
break;
+ case IORING_REGISTER_ZCRX_IFQ:
+ ret = -EINVAL;
+ if (!arg || nr_args != 1)
+ break;
+ ret = io_register_zcrx_ifq(ctx, arg);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
new file mode 100644
index 000000000000..4c53fd4f7bb3
--- /dev/null
+++ b/io_uring/zcrx.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+#include <linux/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "kbuf.h"
+#include "memmap.h"
+#include "zcrx.h"
+
+#define IO_RQ_MAX_ENTRIES 32768
+
+static int io_allocate_rbuf_ring(struct io_zcrx_ifq *ifq,
+ struct io_uring_zcrx_ifq_reg *reg)
+{
+ size_t off, size;
+ void *ptr;
+
+ off = sizeof(struct io_uring);
+ size = off + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries;
+
+ ptr = io_pages_map(&ifq->rqe_pages, &ifq->n_rqe_pages, size);
+ if (IS_ERR(ptr))
+ return PTR_ERR(ptr);
+
+ ifq->rq_ring = (struct io_uring *)ptr;
+ ifq->rqes = (struct io_uring_zcrx_rqe *)(ptr + off);
+ return 0;
+}
+
+static void io_free_rbuf_ring(struct io_zcrx_ifq *ifq)
+{
+ io_pages_unmap(ifq->rq_ring, &ifq->rqe_pages, &ifq->n_rqe_pages, true);
+ ifq->rq_ring = NULL;
+ ifq->rqes = NULL;
+}
+
+static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
+{
+ struct io_zcrx_ifq *ifq;
+
+ ifq = kzalloc(sizeof(*ifq), GFP_KERNEL);
+ if (!ifq)
+ return NULL;
+
+ ifq->if_rxq = -1;
+ ifq->ctx = ctx;
+ return ifq;
+}
+
+static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
+{
+ io_free_rbuf_ring(ifq);
+ kfree(ifq);
+}
+
+int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+ struct io_uring_zcrx_ifq_reg __user *arg)
+{
+ struct io_uring_zcrx_ifq_reg reg;
+ struct io_zcrx_ifq *ifq;
+ size_t ring_sz, rqes_sz;
+ int ret;
+
+ /*
+ * 1. Interface queue allocation.
+ * 2. It can observe data destined for sockets of other tasks.
+ */
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ /* mandatory io_uring features for zc rx */
+ if (!(ctx->flags & IORING_SETUP_DEFER_TASKRUN &&
+ ctx->flags & IORING_SETUP_CQE32))
+ return -EINVAL;
+ if (ctx->ifq)
+ return -EBUSY;
+ if (copy_from_user(®, arg, sizeof(reg)))
+ return -EFAULT;
+ if (reg.__resv[0] || reg.__resv[1] || reg.__resv[2])
+ return -EINVAL;
+ if (reg.if_rxq == -1 || !reg.rq_entries || reg.flags)
+ return -EINVAL;
+ if (reg.rq_entries > IO_RQ_MAX_ENTRIES) {
+ if (!(ctx->flags & IORING_SETUP_CLAMP))
+ return -EINVAL;
+ reg.rq_entries = IO_RQ_MAX_ENTRIES;
+ }
+ reg.rq_entries = roundup_pow_of_two(reg.rq_entries);
+
+ if (!reg.area_ptr)
+ return -EFAULT;
+
+ ifq = io_zcrx_ifq_alloc(ctx);
+ if (!ifq)
+ return -ENOMEM;
+
+ ret = io_allocate_rbuf_ring(ifq, ®);
+ if (ret)
+ goto err;
+
+ ifq->rq_entries = reg.rq_entries;
+ ifq->if_rxq = reg.if_rxq;
+
+ ring_sz = sizeof(struct io_uring);
+ rqes_sz = sizeof(struct io_uring_zcrx_rqe) * ifq->rq_entries;
+ reg.offsets.mmap_sz = ring_sz + rqes_sz;
+ reg.offsets.rqes = ring_sz;
+ reg.offsets.head = offsetof(struct io_uring, head);
+ reg.offsets.tail = offsetof(struct io_uring, tail);
+
+ if (copy_to_user(arg, ®, sizeof(reg))) {
+ ret = -EFAULT;
+ goto err;
+ }
+
+ ctx->ifq = ifq;
+ return 0;
+err:
+ io_zcrx_ifq_free(ifq);
+ return ret;
+}
+
+void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+ struct io_zcrx_ifq *ifq = ctx->ifq;
+
+ lockdep_assert_held(&ctx->uring_lock);
+
+ if (!ifq)
+ return;
+
+ ctx->ifq = NULL;
+ io_zcrx_ifq_free(ifq);
+}
+
+void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+ lockdep_assert_held(&ctx->uring_lock);
+}
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
new file mode 100644
index 000000000000..1f76eecac5fd
--- /dev/null
+++ b/io_uring/zcrx.h
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_ZC_RX_H
+#define IOU_ZC_RX_H
+
+#include <linux/io_uring_types.h>
+
+struct io_zcrx_ifq {
+ struct io_ring_ctx *ctx;
+ struct net_device *dev;
+ struct io_uring *rq_ring;
+ struct io_uring_zcrx_rqe *rqes;
+ u32 rq_entries;
+
+ unsigned short n_rqe_pages;
+ struct page **rqe_pages;
+
+ u32 if_rxq;
+};
+
+#if defined(CONFIG_IO_URING_ZCRX)
+int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+ struct io_uring_zcrx_ifq_reg __user *arg);
+void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx);
+void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx);
+#else
+static inline int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
+ struct io_uring_zcrx_ifq_reg __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+static inline void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+}
+static inline void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
+{
+}
+#endif
+
+#endif
--
2.43.5
next prev parent reply other threads:[~2024-10-29 23:06 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-29 23:05 [PATCH v7 00/15] io_uring zero copy rx David Wei
2024-10-29 23:05 ` [PATCH v7 01/15] net: prefix devmem specific helpers David Wei
2024-10-29 23:05 ` [PATCH v7 02/15] net: generalise net_iov chunk owners David Wei
2024-10-29 23:05 ` [PATCH v7 03/15] net: page_pool: create hooks for custom page providers David Wei
2024-10-29 23:05 ` [PATCH v7 04/15] net: prepare for non devmem TCP memory providers David Wei
2024-10-29 23:05 ` [PATCH v7 05/15] net: page_pool: add ->scrub mem provider callback David Wei
2024-10-29 23:05 ` [PATCH v7 06/15] net: page pool: add helper creating area from pages David Wei
2024-10-29 23:05 ` [PATCH v7 07/15] net: page_pool: introduce page_pool_mp_return_in_cache David Wei
2024-10-29 23:05 ` [PATCH v7 08/15] net: add helper executing custom callback from napi David Wei
2024-10-29 23:05 ` David Wei [this message]
2024-10-29 23:05 ` [PATCH v7 10/15] io_uring/zcrx: add io_zcrx_area David Wei
2024-10-29 23:05 ` [PATCH v7 11/15] io_uring/zcrx: implement zerocopy receive pp memory provider David Wei
2024-10-29 23:05 ` [PATCH v7 12/15] io_uring/zcrx: add io_recvzc request David Wei
2024-10-29 23:05 ` [PATCH v7 13/15] io_uring/zcrx: set pp memory provider for an rx queue David Wei
2024-10-29 23:05 ` [PATCH v7 14/15] io_uring/zcrx: add copy fallback David Wei
2024-10-29 23:05 ` [PATCH v7 15/15] io_uring/zcrx: throttle receive requests 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 \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[email protected] \
[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