Merge tag 'for-6.15/io_uring-rx-zc-20250325' of git://git.kernel.dk/linux

Pull io_uring zero-copy receive support from Jens Axboe:
 "This adds support for zero-copy receive with io_uring, enabling fast
  bulk receive of data directly into application memory, rather than
  needing to copy the data out of kernel memory.

  While this version only supports host memory as that was the initial
  target, other memory types are planned as well, with notably GPU
  memory coming next.

  This work depends on some networking components which were queued up
  on the networking side, but have now landed in your tree.

  This is the work of Pavel Begunkov and David Wei. From the v14 posting:

    'We configure a page pool that a driver uses to fill a hw rx queue
     to hand out user pages instead of kernel pages. Any data that ends
     up hitting this hw rx queue will thus be dma'd into userspace
     memory directly, without needing to be bounced through kernel
     memory. 'Reading' data out of a socket instead becomes a
     _notification_ mechanism, where the kernel tells userspace where
     the data is. The overall approach is similar to the devmem TCP
     proposal

     This relies on hw header/data split, flow steering and RSS to
     ensure packet headers remain in kernel memory and only desired
     flows hit a hw rx queue configured for zero copy. Configuring this
     is outside of the scope of this patchset.

     We share netdev core infra with devmem TCP. The main difference is
     that io_uring is used for the uAPI and the lifetime of all objects
     are bound to an io_uring instance. Data is 'read' using a new
     io_uring request type. When done, data is returned via a new shared
     refill queue. A zero copy page pool refills a hw rx queue from this
     refill queue directly. Of course, the lifetime of these data
     buffers are managed by io_uring rather than the networking stack,
     with different refcounting rules.

     This patchset is the first step adding basic zero copy support. We
     will extend this iteratively with new features e.g. dynamically
     allocated zero copy areas, THP support, dmabuf support, improved
     copy fallback, general optimisations and more'

  In a local setup, I was able to saturate a 200G link with a single CPU
  core, and at netdev conf 0x19 earlier this month, Jamal reported
  188Gbit of bandwidth using a single core (no HT, including soft-irq).

  Safe to say the efficiency is there, as bigger links would be needed
  to find the per-core limit, and it's considerably more efficient and
  faster than the existing devmem solution"

* tag 'for-6.15/io_uring-rx-zc-20250325' of git://git.kernel.dk/linux:
  io_uring/zcrx: add selftest case for recvzc with read limit
  io_uring/zcrx: add a read limit to recvzc requests
  io_uring: add missing IORING_MAP_OFF_ZCRX_REGION in io_uring_mmap
  io_uring: Rename KConfig to Kconfig
  io_uring/zcrx: fix leaks on failed registration
  io_uring/zcrx: recheck ifq on shutdown
  io_uring/zcrx: add selftest
  net: add documentation for io_uring zcrx
  io_uring/zcrx: add copy fallback
  io_uring/zcrx: throttle receive requests
  io_uring/zcrx: set pp memory provider for an rx queue
  io_uring/zcrx: add io_recvzc request
  io_uring/zcrx: dma-map area for the device
  io_uring/zcrx: implement zerocopy receive pp memory provider
  io_uring/zcrx: grab a net device
  io_uring/zcrx: add io_zcrx_area
  io_uring/zcrx: add interface queue and refill queue

22 files changed, 1988 insertions, 2 deletions

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 058193ed2eeb..c64133d309bf 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -63,6 +63,7 @@ Contents:
    gtp
    ila
    ioam6-sysctl
+   iou-zcrx
    ip_dynaddr
    ipsec
    ip-sysctl
diff --git a/Documentation/networking/iou-zcrx.rst b/Documentation/networking/iou-zcrx.rst
new file mode 100644
index 000000000000..0127319b30bb
--- /dev/null
+++ b/Documentation/networking/iou-zcrx.rst
@@ -0,0 +1,202 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================
+io_uring zero copy Rx
+=====================
+
+Introduction
+============
+
+io_uring zero copy Rx (ZC Rx) is a feature that removes kernel-to-user copy on
+the network receive path, allowing packet data to be received directly into
+userspace memory. This feature is different to TCP_ZEROCOPY_RECEIVE in that
+there are no strict alignment requirements and no need to mmap()/munmap().
+Compared to kernel bypass solutions such as e.g. DPDK, the packet headers are
+processed by the kernel TCP stack as normal.
+
+NIC HW Requirements
+===================
+
+Several NIC HW features are required for io_uring ZC Rx to work. For now the
+kernel API does not configure the NIC and it must be done by the user.
+
+Header/data split
+-----------------
+
+Required to split packets at the L4 boundary into a header and a payload.
+Headers are received into kernel memory as normal and processed by the TCP
+stack as normal. Payloads are received into userspace memory directly.
+
+Flow steering
+-------------
+
+Specific HW Rx queues are configured for this feature, but modern NICs
+typically distribute flows across all HW Rx queues. Flow steering is required
+to ensure that only desired flows are directed towards HW queues that are
+configured for io_uring ZC Rx.
+
+RSS
+---
+
+In addition to flow steering above, RSS is required to steer all other non-zero
+copy flows away from queues that are configured for io_uring ZC Rx.
+
+Usage
+=====
+
+Setup NIC
+---------
+
+Must be done out of band for now.
+
+Ensure there are at least two queues::
+
+  ethtool -L eth0 combined 2
+
+Enable header/data split::
+
+  ethtool -G eth0 tcp-data-split on
+
+Carve out half of the HW Rx queues for zero copy using RSS::
+
+  ethtool -X eth0 equal 1
+
+Set up flow steering, bearing in mind that queues are 0-indexed::
+
+  ethtool -N eth0 flow-type tcp6 ... action 1
+
+Setup io_uring
+--------------
+
+This section describes the low level io_uring kernel API. Please refer to
+liburing documentation for how to use the higher level API.
+
+Create an io_uring instance with the following required setup flags::
+
+  IORING_SETUP_SINGLE_ISSUER
+  IORING_SETUP_DEFER_TASKRUN
+  IORING_SETUP_CQE32
+
+Create memory area
+------------------
+
+Allocate userspace memory area for receiving zero copy data::
+
+  void *area_ptr = mmap(NULL, area_size,
+                        PROT_READ | PROT_WRITE,
+                        MAP_ANONYMOUS | MAP_PRIVATE,
+                        0, 0);
+
+Create refill ring
+------------------
+
+Allocate memory for a shared ringbuf used for returning consumed buffers::
+
+  void *ring_ptr = mmap(NULL, ring_size,
+                        PROT_READ | PROT_WRITE,
+                        MAP_ANONYMOUS | MAP_PRIVATE,
+                        0, 0);
+
+This refill ring consists of some space for the header, followed by an array of
+``struct io_uring_zcrx_rqe``::
+
+  size_t rq_entries = 4096;
+  size_t ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe) + PAGE_SIZE;
+  /* align to page size */
+  ring_size = (ring_size + (PAGE_SIZE - 1)) & ~(PAGE_SIZE - 1);
+
+Register ZC Rx
+--------------
+
+Fill in registration structs::
+
+  struct io_uring_zcrx_area_reg area_reg = {
+    .addr = (__u64)(unsigned long)area_ptr,
+    .len = area_size,
+    .flags = 0,
+  };
+
+  struct io_uring_region_desc region_reg = {
+    .user_addr = (__u64)(unsigned long)ring_ptr,
+    .size = ring_size,
+    .flags = IORING_MEM_REGION_TYPE_USER,
+  };
+
+  struct io_uring_zcrx_ifq_reg reg = {
+    .if_idx = if_nametoindex("eth0"),
+    /* this is the HW queue with desired flow steered into it */
+    .if_rxq = 1,
+    .rq_entries = rq_entries,
+    .area_ptr = (__u64)(unsigned long)&area_reg,
+    .region_ptr = (__u64)(unsigned long)&region_reg,
+  };
+
+Register with kernel::
+
+  io_uring_register_ifq(ring, &reg);
+
+Map refill ring
+---------------
+
+The kernel fills in fields for the refill ring in the registration ``struct
+io_uring_zcrx_ifq_reg``. Map it into userspace::
+
+  struct io_uring_zcrx_rq refill_ring;
+
+  refill_ring.khead = (unsigned *)((char *)ring_ptr + reg.offsets.head);
+  refill_ring.khead = (unsigned *)((char *)ring_ptr + reg.offsets.tail);
+  refill_ring.rqes =
+    (struct io_uring_zcrx_rqe *)((char *)ring_ptr + reg.offsets.rqes);
+  refill_ring.rq_tail = 0;
+  refill_ring.ring_ptr = ring_ptr;
+
+Receiving data
+--------------
+
+Prepare a zero copy recv request::
+
+  struct io_uring_sqe *sqe;
+
+  sqe = io_uring_get_sqe(ring);
+  io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, fd, NULL, 0, 0);
+  sqe->ioprio |= IORING_RECV_MULTISHOT;
+
+Now, submit and wait::
+
+  io_uring_submit_and_wait(ring, 1);
+
+Finally, process completions::
+
+  struct io_uring_cqe *cqe;
+  unsigned int count = 0;
+  unsigned int head;
+
+  io_uring_for_each_cqe(ring, head, cqe) {
+    struct io_uring_zcrx_cqe *rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+
+    unsigned long mask = (1ULL << IORING_ZCRX_AREA_SHIFT) - 1;
+    unsigned char *data = area_ptr + (rcqe->off & mask);
+    /* do something with the data */
+
+    count++;
+  }
+  io_uring_cq_advance(ring, count);
+
+Recycling buffers
+-----------------
+
+Return buffers back to the kernel to be used again::
+
+  struct io_uring_zcrx_rqe *rqe;
+  unsigned mask = refill_ring.ring_entries - 1;
+  rqe = &refill_ring.rqes[refill_ring.rq_tail & mask];
+
+  unsigned long area_offset = rcqe->off & ~IORING_ZCRX_AREA_MASK;
+  rqe->off = area_offset | area_reg.rq_area_token;
+  rqe->len = cqe->res;
+  IO_URING_WRITE_ONCE(*refill_ring.ktail, ++refill_ring.rq_tail);
+
+Testing
+=======
+
+See ``tools/testing/selftests/drivers/net/hw/iou-zcrx.c``
diff --git a/Kconfig b/Kconfig
index 745bc773f567..307e581144de 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 72aac84dca93..35fc241c4672 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -40,6 +40,8 @@ enum io_uring_cmd_flags {
 	IO_URING_F_TASK_DEAD		= (1 << 13),
 };
 
+struct io_zcrx_ifq;
+
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };
@@ -384,6 +386,8 @@ struct io_ring_ctx {
 	struct wait_queue_head		poll_wq;
 	struct io_restriction		restrictions;
 
+	struct io_zcrx_ifq		*ifq;
+
 	u32			pers_next;
 	struct xarray		personalities;
 
@@ -436,6 +440,8 @@ struct io_ring_ctx {
 	struct io_mapped_region		ring_region;
 	/* used for optimised request parameter and wait argument passing  */
 	struct io_mapped_region		param_region;
+	/* just one zcrx per ring for now, will move to io_zcrx_ifq eventually */
+	struct io_mapped_region		zcrx_region;
 };
 
 /*
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 0d6c83c8d1cf..6a446e338162 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -87,6 +87,7 @@ struct io_uring_sqe {
 	union {
 		__s32	splice_fd_in;
 		__u32	file_index;
+		__u32	zcrx_ifq_idx;
 		__u32	optlen;
 		struct {
 			__u16	addr_len;
@@ -278,6 +279,7 @@ enum io_uring_op {
 	IORING_OP_FTRUNCATE,
 	IORING_OP_BIND,
 	IORING_OP_LISTEN,
+	IORING_OP_RECV_ZC,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -641,7 +643,8 @@ enum io_uring_register_op {
 	/* send MSG_RING without having a ring */
 	IORING_REGISTER_SEND_MSG_RING		= 31,
 
-	/* 32 reserved for zc rx */
+	/* register a netdev hw rx queue for zerocopy */
+	IORING_REGISTER_ZCRX_IFQ		= 32,
 
 	/* resize CQ ring */
 	IORING_REGISTER_RESIZE_RINGS		= 33,
@@ -958,6 +961,55 @@ 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	__resv2;
+	__u64	__resv[2];
+};
+
+struct io_uring_zcrx_area_reg {
+	__u64	addr;
+	__u64	len;
+	__u64	rq_area_token;
+	__u32	flags;
+	__u32	__resv1;
+	__u64	__resv2[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 */
+	__u64	region_ptr; /* struct io_uring_region_desc * */
+
+	struct io_uring_zcrx_offsets offsets;
+	__u64	__resv[4];
+};
+
 #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 d695b60dba4f..98e48339d84d 100644
--- a/io_uring/Makefile
+++ b/io_uring/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					epoll.o statx.o timeout.o fdinfo.o \
 					cancel.o waitid.o register.o \
 					truncate.o memmap.o alloc_cache.o
+obj-$(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 078475447264..f743581cc81b 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -97,6 +97,7 @@
 #include "uring_cmd.h"
 #include "msg_ring.h"
 #include "memmap.h"
+#include "zcrx.h"
 
 #include "timeout.h"
 #include "poll.h"
@@ -2732,6 +2733,7 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 	mutex_lock(&ctx->uring_lock);
 	io_sqe_buffers_unregister(ctx);
 	io_sqe_files_unregister(ctx);
+	io_unregister_zcrx_ifqs(ctx);
 	io_cqring_overflow_kill(ctx);
 	io_eventfd_unregister(ctx);
 	io_free_alloc_caches(ctx);
@@ -2891,6 +2893,11 @@ 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/io_uring.h b/io_uring/io_uring.h
index 372129e24372..b95dab77e32d 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -189,6 +189,16 @@ static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret
 	return io_get_cqe_overflow(ctx, ret, false);
 }
 
+static inline bool io_defer_get_uncommited_cqe(struct io_ring_ctx *ctx,
+					       struct io_uring_cqe **cqe_ret)
+{
+	io_lockdep_assert_cq_locked(ctx);
+
+	ctx->cq_extra++;
+	ctx->submit_state.cq_flush = true;
+	return io_get_cqe(ctx, cqe_ret);
+}
+
 static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx,
 					    struct io_kiocb *req)
 {
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 361134544427..76fcc79656b0 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -271,6 +271,8 @@ static struct io_mapped_region *io_mmap_get_region(struct io_ring_ctx *ctx,
 		return io_pbuf_get_region(ctx, bgid);
 	case IORING_MAP_OFF_PARAM_REGION:
 		return &ctx->param_region;
+	case IORING_MAP_OFF_ZCRX_REGION:
+		return &ctx->zcrx_region;
 	}
 	return NULL;
 }
diff --git a/io_uring/memmap.h b/io_uring/memmap.h
index c898dcba2b4e..dad0aa5b1b45 100644
--- a/io_uring/memmap.h
+++ b/io_uring/memmap.h
@@ -2,6 +2,7 @@
 #define IO_URING_MEMMAP_H
 
 #define IORING_MAP_OFF_PARAM_REGION		0x20000000ULL
+#define IORING_MAP_OFF_ZCRX_REGION		0x30000000ULL
 
 struct page **io_pin_pages(unsigned long ubuf, unsigned long len, int *npages);
 
diff --git a/io_uring/net.c b/io_uring/net.c
index 3fc39af5159e..89cd45bacd7c 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 "zcrx.h"
 
 #if defined(CONFIG_NET)
 struct io_shutdown {
@@ -88,6 +89,14 @@ struct io_sr_msg {
  */
 #define MULTISHOT_MAX_RETRY	32
 
+struct io_recvzc {
+	struct file			*file;
+	unsigned			msg_flags;
+	u16				flags;
+	u32				len;
+	struct io_zcrx_ifq		*ifq;
+};
+
 int io_shutdown_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 {
 	struct io_shutdown *shutdown = io_kiocb_to_cmd(req, struct io_shutdown);
@@ -1199,6 +1208,81 @@ out_free:
 	return ret;
 }
 
+int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+	unsigned ifq_idx;
+
+	if (unlikely(sqe->file_index || sqe->addr2 || sqe->addr ||
+		     sqe->addr3))
+		return -EINVAL;
+
+	ifq_idx = READ_ONCE(sqe->zcrx_ifq_idx);
+	if (ifq_idx != 0)
+		return -EINVAL;
+	zc->ifq = req->ctx->ifq;
+	if (!zc->ifq)
+		return -EINVAL;
+	zc->len = READ_ONCE(sqe->len);
+	zc->flags = READ_ONCE(sqe->ioprio);
+	zc->msg_flags = READ_ONCE(sqe->msg_flags);
+	if (zc->msg_flags)
+		return -EINVAL;
+	if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | IORING_RECV_MULTISHOT))
+		return -EINVAL;
+	/* multishot required */
+	if (!(zc->flags & IORING_RECV_MULTISHOT))
+		return -EINVAL;
+	/* All data completions are posted as aux CQEs. */
+	req->flags |= REQ_F_APOLL_MULTISHOT;
+
+	return 0;
+}
+
+int io_recvzc(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
+	struct socket *sock;
+	unsigned int len;
+	int ret;
+
+	if (!(req->flags & REQ_F_POLLED) &&
+	    (zc->flags & IORING_RECVSEND_POLL_FIRST))
+		return -EAGAIN;
+
+	sock = sock_from_file(req->file);
+	if (unlikely(!sock))
+		return -ENOTSOCK;
+
+	len = zc->len;
+	ret = io_zcrx_recv(req, zc->ifq, sock, zc->msg_flags | MSG_DONTWAIT,
+			   issue_flags, &zc->len);
+	if (len && zc->len == 0) {
+		io_req_set_res(req, 0, 0);
+
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			return IOU_STOP_MULTISHOT;
+		return IOU_OK;
+	}
+	if (unlikely(ret <= 0) && ret != -EAGAIN) {
+		if (ret == -ERESTARTSYS)
+			ret = -EINTR;
+		if (ret == IOU_REQUEUE)
+			return IOU_REQUEUE;
+
+		req_set_fail(req);
+		io_req_set_res(req, ret, 0);
+
+		if (issue_flags & IO_URING_F_MULTISHOT)
+			return IOU_STOP_MULTISHOT;
+		return IOU_OK;
+	}
+
+	if (issue_flags & IO_URING_F_MULTISHOT)
+		return IOU_ISSUE_SKIP_COMPLETE;
+	return -EAGAIN;
+}
+
 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/opdef.c b/io_uring/opdef.c
index 306fd9c48b44..9511262c513e 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -37,6 +37,7 @@
 #include "waitid.h"
 #include "futex.h"
 #include "truncate.h"
+#include "zcrx.h"
 
 static int io_no_issue(struct io_kiocb *req, unsigned int issue_flags)
 {
@@ -516,6 +517,18 @@ const struct io_issue_def io_issue_defs[] = {
 		.prep			= io_eopnotsupp_prep,
 #endif
 	},
+	[IORING_OP_RECV_ZC] = {
+		.needs_file		= 1,
+		.unbound_nonreg_file	= 1,
+		.pollin			= 1,
+		.ioprio			= 1,
+#if defined(CONFIG_NET)
+		.prep			= io_recvzc_prep,
+		.issue			= io_recvzc,
+#else
+		.prep			= io_eopnotsupp_prep,
+#endif
+	},
 };
 
 const struct io_cold_def io_cold_defs[] = {
@@ -745,6 +758,9 @@ const struct io_cold_def io_cold_defs[] = {
 	[IORING_OP_LISTEN] = {
 		.name			= "LISTEN",
 	},
+	[IORING_OP_RECV_ZC] = {
+		.name			= "RECV_ZC",
+	},
 };
 
 const char *io_uring_get_opcode(u8 opcode)
diff --git a/io_uring/register.c b/io_uring/register.c
index 9a4d2fbce4ae..cc23a4c205cd 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -30,6 +30,7 @@
 #include "eventfd.h"
 #include "msg_ring.h"
 #include "memmap.h"
+#include "zcrx.h"
 
 #define IORING_MAX_RESTRICTIONS	(IORING_RESTRICTION_LAST + \
 				 IORING_REGISTER_LAST + IORING_OP_LAST)
@@ -813,6 +814,12 @@ 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;
 	case IORING_REGISTER_RESIZE_RINGS:
 		ret = -EINVAL;
 		if (!arg || nr_args != 1)
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 5fff6ba2b7c0..a59563fbb4ad 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -80,7 +80,7 @@ static int io_account_mem(struct io_ring_ctx *ctx, unsigned long nr_pages)
 	return 0;
 }
 
-static int io_buffer_validate(struct iovec *iov)
+int io_buffer_validate(struct iovec *iov)
 {
 	unsigned long tmp, acct_len = iov->iov_len + (PAGE_SIZE - 1);
 
diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index f10a1252b3e9..284e300e63fb 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -76,6 +76,7 @@ int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg,
 			    unsigned size, unsigned type);
 int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg,
 			unsigned int size, unsigned int type);
+int io_buffer_validate(struct iovec *iov);
 
 bool io_check_coalesce_buffer(struct page **page_array, int nr_pages,
 			      struct io_imu_folio_data *data);
diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
new file mode 100644
index 000000000000..9c95b5b6ec4e
--- /dev/null
+++ b/io_uring/zcrx.c
@@ -0,0 +1,960 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/dma-map-ops.h>
+#include <linux/mm.h>
+#include <linux/nospec.h>
+#include <linux/io_uring.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff_ref.h>
+
+#include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
+#include <net/netlink.h>
+#include <net/netdev_rx_queue.h>
+#include <net/tcp.h>
+#include <net/rps.h>
+
+#include <trace/events/page_pool.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "kbuf.h"
+#include "memmap.h"
+#include "zcrx.h"
+#include "rsrc.h"
+
+#define IO_DMA_ATTR (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+
+static void __io_zcrx_unmap_area(struct io_zcrx_ifq *ifq,
+				 struct io_zcrx_area *area, int nr_mapped)
+{
+	int i;
+
+	for (i = 0; i < nr_mapped; i++) {
+		struct net_iov *niov = &area->nia.niovs[i];
+		dma_addr_t dma;
+
+		dma = page_pool_get_dma_addr_netmem(net_iov_to_netmem(niov));
+		dma_unmap_page_attrs(ifq->dev, dma, PAGE_SIZE,
+				     DMA_FROM_DEVICE, IO_DMA_ATTR);
+		net_mp_niov_set_dma_addr(niov, 0);
+	}
+}
+
+static void io_zcrx_unmap_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
+{
+	if (area->is_mapped)
+		__io_zcrx_unmap_area(ifq, area, area->nia.num_niovs);
+}
+
+static int io_zcrx_map_area(struct io_zcrx_ifq *ifq, struct io_zcrx_area *area)
+{
+	int i;
+
+	for (i = 0; i < area->nia.num_niovs; i++) {
+		struct net_iov *niov = &area->nia.niovs[i];
+		dma_addr_t dma;
+
+		dma = dma_map_page_attrs(ifq->dev, area->pages[i], 0, PAGE_SIZE,
+					 DMA_FROM_DEVICE, IO_DMA_ATTR);
+		if (dma_mapping_error(ifq->dev, dma))
+			break;
+		if (net_mp_niov_set_dma_addr(niov, dma)) {
+			dma_unmap_page_attrs(ifq->dev, dma, PAGE_SIZE,
+					     DMA_FROM_DEVICE, IO_DMA_ATTR);
+			break;
+		}
+	}
+
+	if (i != area->nia.num_niovs) {
+		__io_zcrx_unmap_area(ifq, area, i);
+		return -EINVAL;
+	}
+
+	area->is_mapped = true;
+	return 0;
+}
+
+static void io_zcrx_sync_for_device(const struct page_pool *pool,
+				    struct net_iov *niov)
+{
+#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
+	dma_addr_t dma_addr;
+
+	if (!dma_dev_need_sync(pool->p.dev))
+		return;
+
+	dma_addr = page_pool_get_dma_addr_netmem(net_iov_to_netmem(niov));
+	__dma_sync_single_for_device(pool->p.dev, dma_addr + pool->p.offset,
+				     PAGE_SIZE, pool->p.dma_dir);
+#endif
+}
+
+#define IO_RQ_MAX_ENTRIES		32768
+
+#define IO_SKBS_PER_CALL_LIMIT	20
+
+struct io_zcrx_args {
+	struct io_kiocb		*req;
+	struct io_zcrx_ifq	*ifq;
+	struct socket		*sock;
+	unsigned		nr_skbs;
+};
+
+static const struct memory_provider_ops io_uring_pp_zc_ops;
+
+static inline struct io_zcrx_area *io_zcrx_iov_to_area(const struct net_iov *niov)
+{
+	struct net_iov_area *owner = net_iov_owner(niov);
+
+	return container_of(owner, struct io_zcrx_area, nia);
+}
+
+static inline atomic_t *io_get_user_counter(struct net_iov *niov)
+{
+	struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+	return &area->user_refs[net_iov_idx(niov)];
+}
+
+static bool io_zcrx_put_niov_uref(struct net_iov *niov)
+{
+	atomic_t *uref = io_get_user_counter(niov);
+
+	if (unlikely(!atomic_read(uref)))
+		return false;
+	atomic_dec(uref);
+	return true;
+}
+
+static void io_zcrx_get_niov_uref(struct net_iov *niov)
+{
+	atomic_inc(io_get_user_counter(niov));
+}
+
+static inline struct page *io_zcrx_iov_page(const struct net_iov *niov)
+{
+	struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
+
+	return area->pages[net_iov_idx(niov)];
+}
+
+static int io_allocate_rbuf_ring(struct io_zcrx_ifq *ifq,
+				 struct io_uring_zcrx_ifq_reg *reg,
+				 struct io_uring_region_desc *rd)
+{
+	size_t off, size;
+	void *ptr;
+	int ret;
+
+	off = sizeof(struct io_uring);
+	size = off + sizeof(struct io_uring_zcrx_rqe) * reg->rq_entries;
+	if (size > rd->size)
+		return -EINVAL;
+
+	ret = io_create_region_mmap_safe(ifq->ctx, &ifq->ctx->zcrx_region, rd,
+					 IORING_MAP_OFF_ZCRX_REGION);
+	if (ret < 0)
+		return ret;
+
+	ptr = io_region_get_ptr(&ifq->ctx->zcrx_region);
+	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_free_region(ifq->ctx, &ifq->ctx->zcrx_region);
+	ifq->rq_ring = NULL;
+	ifq->rqes = NULL;
+}
+
+static void io_zcrx_free_area(struct io_zcrx_area *area)
+{
+	io_zcrx_unmap_area(area->ifq, area);
+
+	kvfree(area->freelist);
+	kvfree(area->nia.niovs);
+	kvfree(area->user_refs);
+	if (area->pages) {
+		unpin_user_pages(area->pages, area->nia.num_niovs);
+		kvfree(area->pages);
+	}
+	kfree(area);
+}
+
+static int io_zcrx_create_area(struct io_zcrx_ifq *ifq,
+			       struct io_zcrx_area **res,
+			       struct io_uring_zcrx_area_reg *area_reg)
+{
+	struct io_zcrx_area *area;
+	int i, ret, nr_pages;
+	struct iovec iov;
+
+	if (area_reg->flags || area_reg->rq_area_token)
+		return -EINVAL;
+	if (area_reg->__resv1 || area_reg->__resv2[0] || area_reg->__resv2[1]