Re: [PATCH v2 3/7] virtio: Add the pasta vhost-net interface and implementation

[Laurent Vivier <lvivier@redhat.com>]

On 10/16/26 22:49, aerosouund wrote:
> From: Ammar Yasser <aerosound161@gmail.com>
> 
> Add vhost.c and vhost.h which define the api and implementation for
> pasta vhost acceleration
> 
> - vq_state/vhost_vq_state[]: our own view of each virtqueue, which the
>    kernel doesn't track for us: descriptors ready to hand back, how far
>    we've read the used ring, and the next descriptor to allocate
> - vring_desc, vring_avail_all, vring_used_all, vhost_memory: the rings
>    and the region table shared with the kernel
> - vhost_setup_net: open /dev/vhost-net and negotiate VIRTIO_F_VERSION_1
>    and VHOST_NET_F_VIRTIO_NET_HDR. Failure is fatal only if
>    --vhost-kernel is set to 'on'.
> - vhost_setup_eventfds: create, register and watch the call, kick and
>    error eventfds for one queue
> - vhost_setup_memory_table: register the buffers the kernel may touch.
>    pasta has no guest, so each region maps guest_phys_addr onto the
>    identical userspace_addr, making GPA translation an identity mapping.
>    This function uses the *_register_memory_regions functions created per
>    protocol and for general purpose buffers.
> - vhost_set_vring: publish a vring's addresses, bind the tap fd as its
>    backend and lay out its descriptors
> - vhost_rx_descriptor_handoff, vhost_kick: hand consumed descriptors back
>    and notify the kernel unless it says it's already polling
> 
> Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
> Signed-off-by: Ammar Yasser <aerosound161@gmail.com>
> ---
>   Makefile  |   2 +-
>   tcp_buf.c |  22 +++-
>   tcp_buf.h |   4 +
>   udp.c     |  20 ++++
>   udp.h     |   3 +
>   util.c    |  18 ++++
>   util.h    |   2 +
>   vhost.c   | 295 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
>   vhost.h   |  91 +++++++++++++++++
>   9 files changed, 455 insertions(+), 2 deletions(-)
>   create mode 100644 vhost.c
>   create mode 100644 vhost.h
> 
> diff --git a/Makefile b/Makefile
> index f6c87b1..6f11e4b 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -38,7 +38,7 @@ PASST_SRCS = arch.c arp.c bitmap.c checksum.c conf.c dhcp.c dhcpv6.c \
>   	isolation.c lineread.c log.c mld.c ndp.c netlink.c migrate.c packet.c \
>   	parse.c passt.c pasta.c pcap.c pif.c repair.c serialise.c tap.c tcp.c \
>   	tcp_buf.c tcp_splice.c tcp_vu.c udp.c udp_flow.c udp_vu.c util.c \
> -	vhost_user.c virtio.c vu_common.c
> +	vhost.c vhost_user.c virtio.c vu_common.c
>   PASST_REPAIR_SRCS = passt-repair.c
>   PESTO_SRCS = pesto.c bitmap.c fwd_rule.c inany.c ip.c lineread.c parse.c \
>   	serialise.c
> diff --git a/tcp_buf.c b/tcp_buf.c
> index 72c4541..dd80384 100644
> --- a/tcp_buf.c
> +++ b/tcp_buf.c
> @@ -31,12 +31,14 @@
>   #include "inany.h"
>   #include "tcp_conn.h"
>   #include "tcp_internal.h"
> -#include "tcp_buf.h"
> +#include "vhost.h"
> 
>   #define TCP_FRAMES_MEM			128
>   #define TCP_FRAMES							   \
>   	(c->mode == MODE_PASTA ? 1 : TCP_FRAMES_MEM)
> 
> +#define TCP_NREGIONS 5
> +
>   /* Static buffers */
> 
>   /* Ethernet header for IPv4 and IPv6 frames */
> @@ -75,6 +77,24 @@ void tcp_update_l2_buf(const unsigned char *eth_d)
>   		eth_update_mac(&tcp_eth_hdr[i], eth_d, NULL);
>   }
> 
> +/**
> + * tcp_register_memory_region() - Register the TCP specific buffers into a memory
> + *                                struct so it can be shared with the kernel.
> + * @vhost_mem: The memory struct to register regions into
> + * @last_idx:  The last index at which memory region has been placed
> + */
> +void tcp_register_memory_regions(union vhost_memory_u *vhost_mem, size_t *last_idx) {

opening brace must be on its own line

> +	if ((*last_idx + TCP_NREGIONS) > N_VHOST_REGIONS)
> +		die("tcp: memory region overflow. maximum is %d, got %zu",
> +		    N_VHOST_REGIONS, *last_idx + TCP_NREGIONS);

multiline body needs opening and closing braces

> +
> +   	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(tcp_payload_tap_hdr);

space before tab in indent

> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(tcp4_payload_ip);
> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(tcp6_payload_ip);
> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(tcp_payload);
> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(tcp_eth_hdr);
> +}
> +
>   /**
>    * tcp_sock_iov_init() - Initialise scatter-gather L2 buffers for IPv4 sockets
>    * @c:		Execution context
> diff --git a/tcp_buf.h b/tcp_buf.h
> index 5d31cea..5e341ed 100644
> --- a/tcp_buf.h
> +++ b/tcp_buf.h
> @@ -6,11 +6,15 @@
>   #ifndef TCP_BUF_H
>   #define TCP_BUF_H
> 
> +union vhost_memory_u;
> +struct tcp_tap_conn;
> +
>   void tcp_sock_iov_init(const struct ctx *c);
>   void tcp_payload_flush(const struct ctx *c, const struct timespec *now);
>   int tcp_buf_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn,
>   			   uint32_t already_sent, const struct timespec *now);
>   int tcp_buf_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags,
>   		      const struct timespec *now);
> +void tcp_register_memory_regions(union vhost_memory_u *vhost_mem, size_t *last_idx);
> 
>   #endif  /*TCP_BUF_H */
> diff --git a/udp.c b/udp.c
> index 505e554..a4355a1 100644
> --- a/udp.c
> +++ b/udp.c
> @@ -118,6 +118,7 @@
>   #include "udp_internal.h"
>   #include "udp_vu.h"
>   #include "epoll_ctl.h"
> +#include "vhost.h"
> 
>   #define UDP_MAX_FRAMES		32  /* max # of frames to receive at once */
> 
> @@ -128,6 +129,8 @@
>   #define UDP_TIMEOUT_DEFAULT		30	/* s */
>   #define UDP_TIMEOUT_STREAM_DEFAULT	120	/* s */
> 
> +#define UDP_NREGIONS 5
> +
>   /* Maximum UDP data to be returned in ICMP messages */
>   #define ICMP4_MAX_DLEN 8
>   #define ICMP6_MAX_DLEN (IPV6_MIN_MTU			\
> @@ -448,6 +451,23 @@ static void udp_send_tap_icmp4(const struct ctx *c,
>   	tap_icmp4_send(c, saddr, eaddr, &msg, tap_omac, msglen);
>   }
> 
> +/**
> + * udp_register_memory_region() - Register the UDP specific buffers into a memory
> + *                                struct so it can be shared with the kernel.
> + * @vhost_mem: The memory struct to register regions into
> + * @last_idx:  The last index at which memory region has been placed
> + */
> +void udp_register_memory_regions(union vhost_memory_u *vhost_mem, size_t *last_idx) {

opening brace on its own line

> +	if ((*last_idx + UDP_NREGIONS) > N_VHOST_REGIONS)
> +		die("udp: memory region overflow. maximum is %d, got %zu",
> +		    N_VHOST_REGIONS, *last_idx + UDP_NREGIONS);

opening and closing braces for the if body

> +
> +   	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(udp_payload);

space before tab in indent

> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(udp_eth_hdr);
> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(udp_iov_recv);
> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(udp_mh_recv);
> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(udp_meta);
> +}
> 
>   /**
>    * udp_send_tap_icmp6() - Construct and send ICMPv6 to local peer
> diff --git a/udp.h b/udp.h
> index b50283e..ebf1a4e 100644
> --- a/udp.h
> +++ b/udp.h
> @@ -11,6 +11,8 @@
> 
>   #include "fwd.h"
> 
> +union vhost_memory_u;
> +
>   void udp_listen_sock_handler(const struct ctx *c, union epoll_ref ref,
>   			     uint32_t events, const struct timespec *now);
>   void udp_sock_handler(const struct ctx *c, union epoll_ref ref,
> @@ -21,6 +23,7 @@ int udp_tap_handler(const struct ctx *c, uint8_t pif,
>   		    const struct timespec *now);
>   int udp_init(struct ctx *c);
>   void udp_update_l2_buf(const unsigned char *eth_d);
> +void udp_register_memory_regions(union vhost_memory_u *vhost_mem, size_t *last_idx);
> 
>   /**
>    * struct udp_ctx - Execution context for UDP
> diff --git a/util.c b/util.c
> index ff1f19f..cafe0ec 100644
> --- a/util.c
> +++ b/util.c
> @@ -33,10 +33,13 @@
>   #include "log.h"
>   #include "pcap.h"
>   #include "serialise.h"
> +#include "vhost.h"
>   #ifdef HAS_GETRANDOM
>   #include <sys/random.h>
>   #endif
> 
> +#define GENERAL_NREGIONS 2
> +
>   /* Zero-filled buffer to pad 802.3 frames, up to 60 (ETH_ZLEN) bytes */
>   uint8_t eth_pad[ETH_ZLEN] = { 0 };
> 
> @@ -453,6 +456,21 @@ int open_in_ns(const struct ctx *c, const char *path, int flags)
>   	return arg.fd;
>   }
> 
> +/**
> + * general_register_memory_region() - Register the general (non protocol specific) buffers
> + *                                    into a memory struct so it can be shared with the kernel.
> + * @vhost_mem: The memory struct to register regions into
> + * @last_idx:  The last index at which memory region has been placed
> + */
> +void general_register_memory_regions(union vhost_memory_u *vhost_mem, size_t *last_idx) {

opening brace on its own line

> +	if ((*last_idx + GENERAL_NREGIONS) > N_VHOST_REGIONS)
> +		die("general: memory region overflow. maximum is %d, got %zu",
> +		    N_VHOST_REGIONS, *last_idx + GENERAL_NREGIONS);

opening and closing braces

> +
> +   	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(pkt_buf);

space before tab in indent

> +	vhost_mem->mem.regions[(*last_idx)++] = VHOST_MEMORY_REGION(eth_pad);
> +}
> +
>   /**
>    * pidfile_write() - Write PID to file, if requested to do so, and close it
>    * @fd:		Open PID file descriptor, closed on exit, -1 to skip writing it
> diff --git a/util.h b/util.h
> index ec2d9ac..11f6877 100644
> --- a/util.h
> +++ b/util.h
> @@ -145,6 +145,7 @@ int do_clone(int (*fn)(void *), char *stack_area, size_t stack_size, int flags,
> 
>   struct ctx;
>   union sockaddr_inany;
> +union vhost_memory_u;
> 
>   int sock_l4(const struct ctx *c, enum epoll_type type,
>   	    const union sockaddr_inany *sa, const char *ifname);
> @@ -170,6 +171,7 @@ int write_remainder(int fd, const struct iovec *iov, size_t iovcnt,
>   int read_remainder(int fd, const struct iovec *iov, size_t cnt, size_t skip);
>   bool snprintf_check(char *str, size_t size, const char *format, ...);
>   long clamped_scale(long x, long y, long lo, long hi, long f);
> +void general_register_memory_regions(union vhost_memory_u *vhost_mem, size_t *last_idx);
> 
>   /**
>    * af_name() - Return name of an address family
> diff --git a/vhost.c b/vhost.c
> new file mode 100644
> index 0000000..a69c4b5
> --- /dev/null
> +++ b/vhost.c
> @@ -0,0 +1,295 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +/* Copyright Red Hat
> + * Author: Ammar Yasser <aerosound161@gmail.com>
> + *
> + * vhost.c - vhost-net (vhost-kernel) acceleration for pasta mode
> + */
> +
> +#include <errno.h>
> +#include <fcntl.h>
> +#include <inttypes.h>
> +#include <stdint.h>
> +#include <string.h>
> +#include <unistd.h>
> +#include <sys/eventfd.h>
> +#include <sys/ioctl.h>
> +
> +#include "util.h"
> +#include "passt.h"
> +#include "vhost.h"
> +#include "epoll_ctl.h"
> +#include "udp.h"
> +#include "tcp_buf.h"
> +
> +struct vq_state vhost_vq_state[2];
> +
> +struct vring_desc_pasta vring_desc[2][VHOST_NDESCS]
> +				__attribute__((aligned(PAGE_SIZE)));
> +
> +struct vring_avail_pasta vring_avail_all[2]
> +				__attribute__((aligned(PAGE_SIZE)));
> +struct vring_used_pasta vring_used_all[2]
> +				__attribute__((aligned(PAGE_SIZE)));
> +
> +union vhost_memory_u vhost_memory = {
> +	.mem = {
> +		.nregions = N_VHOST_REGIONS,
> +	},
> +};
> +
> +/**
> + * vhost_setup_net() - Open and negotiate features on /dev/vhost-net
> + * @c:		Execution context; c->vhost.fd and c->vhost.features are set
> + *		on success, and left untouched on failure
> + *
> + * Failure here means vhost-net isn't usable, not that pasta can't run: the
> + * caller falls back to plain tap operation unless acceleration was required.
> + * That's why nothing in here is fatal.
> + *
> + * Return: 0 on success, -1 if vhost-net is unavailable or unusable
> + */
> +int vhost_setup_net(struct ctx *c)
> +{
> +	const uint64_t req_features = (1ULL << VIRTIO_F_VERSION_1) |
> +				      (1ULL << VHOST_NET_F_VIRTIO_NET_HDR);
> +	uint64_t features;
> +	int vhost_fd;
> +
> +	vhost_fd = open("/dev/vhost-net", O_RDWR | O_NONBLOCK | O_CLOEXEC);
> +	if (vhost_fd < 0) {
> +		debug_perror("Couldn't open /dev/vhost-net");
> +		return -1;
> +	}
> +
> +	if (ioctl(vhost_fd, VHOST_SET_OWNER, NULL) < 0) {
> +		debug_perror("VHOST_SET_OWNER ioctl failed");
> +		goto close_fd;
> +	}
> +
> +	if (ioctl(vhost_fd, VHOST_GET_FEATURES, &features) < 0) {
> +		debug_perror("VHOST_GET_FEATURES ioctl failed");
> +		goto close_fd;
> +	}
> +
> +	if ((features & req_features) != req_features) {
> +		debug("vhost-net is missing features: 0x%016" PRIx64,
> +		      req_features & ~features);
> +		goto close_fd;
> +	}
> +
> +	features = req_features;
> +	if (ioctl(vhost_fd, VHOST_SET_FEATURES, &features) < 0) {
> +		debug_perror("VHOST_SET_FEATURES ioctl failed");
> +		goto close_fd;
> +	}
> +
> +	c->vhost.features = features;
> +	c->vhost.fd = vhost_fd;
> +
> +	return 0;
> +
> +close_fd:
> +	close(vhost_fd);
> +
> +	return -1;
> +}
> +
> +/**
> + * vhost_setup_eventfds() - Set up one queue's eventfds and ring size
> + * @c:		Execution context; c->vhost.fd must already be set
> + * @queue_idx:	Index of the queue (vring) to configure
> + *
> + */
> +void vhost_setup_eventfds(struct ctx *c, int queue_idx)
> +{
> +	struct vhost_vring_file vring_file = { .index = queue_idx };
> +	struct vhost_vring_state state = { .index = queue_idx };
> +	union epoll_ref ref = { 0 };
> +	int vhost_fd = c->vhost.fd;
> +	int rc;
> +
> +	state.num = VHOST_NDESCS;
> +	ref.queue = queue_idx;
> +
> +	vring_file.fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
> +	if (vring_file.fd < 0)
> +		die_perror("Failed to create vhost call eventfd, queue %d",
> +			   queue_idx);
> +	ref.fd = vring_file.fd;
> +
> +	rc = ioctl(vhost_fd, VHOST_SET_VRING_CALL, &vring_file);
> +	if (rc < 0)
> +		die_perror("VHOST_SET_VRING_CALL ioctl failed, queue %d",
> +			   queue_idx);
> +
> +	ref.type = EPOLL_TYPE_VHOST_CALL;
> +	rc = epoll_add(c->epollfd, EPOLLIN, ref);
> +	if (rc < 0)
> +		die_perror("Failed to watch vhost call eventfd, queue %d",
> +			   queue_idx);
> +	c->vhost.vq[queue_idx].call_fd = vring_file.fd;
> +
> +	vring_file.fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
> +	if (vring_file.fd < 0)
> +		die_perror("Failed to create vhost error eventfd, queue %d",
> +			   queue_idx);
> +
> +	rc = ioctl(vhost_fd, VHOST_SET_VRING_ERR, &vring_file);
> +	if (rc < 0)
> +		die_perror("VHOST_SET_VRING_ERR ioctl failed, queue %d",
> +			   queue_idx);
> +
> +	ref.type = EPOLL_TYPE_VHOST_ERROR;
> +	ref.fd = vring_file.fd;
> +	rc = epoll_add(c->epollfd, EPOLLIN, ref);
> +	if (rc < 0)
> +		die_perror("Failed to watch vhost error eventfd, queue %d",
> +			   queue_idx);
> +	c->vhost.vq[queue_idx].err_fd = vring_file.fd;
> +
> +	rc = ioctl(vhost_fd, VHOST_SET_VRING_NUM, &state);
> +	if (rc < 0)
> +		die_perror("VHOST_SET_VRING_NUM ioctl failed, queue %d",
> +			   queue_idx);
> +
> +	vring_file.fd = eventfd(0, EFD_NONBLOCK | EFD_CLOEXEC);
> +	if (vring_file.fd < 0)
> +		die_perror("Failed to create vhost kick eventfd, queue %d",
> +			   queue_idx);
> +
> +	rc = ioctl(vhost_fd, VHOST_SET_VRING_KICK, &vring_file);
> +	if (rc < 0)
> +		die_perror("VHOST_SET_VRING_KICK ioctl failed, queue %d",
> +			   queue_idx);
> +
> +	c->vhost.vq[queue_idx].kick_fd = vring_file.fd;
> +
> +	vhost_vq_state[queue_idx].num_free = VHOST_NDESCS;
> +}
> +
> +/**
> + * vhost_setup_memory_table() - Register the GPA/HVA translation table
> + * @c:		Execution context; c->vhost.fd must already be set
> + *
> + * vhost-net reads the addresses we put in descriptors as guest physical
> + * addresses, and translates them through this table before touching the
> + * memory they refer to. pasta has no guest and no second address space:
> + * the addresses we put there are our own virtual addresses. Every region
> + * below therefore sets guest_phys_addr equal to userspace_addr, so that
> + * GPA == HVA and the translation is an identity mapping.
> + *
> + * Return: 0 on success, -1 on error with errno set
> + */
> +int vhost_setup_memory_table(struct ctx *c) {
> +	size_t region_idx = 0;
> +
> +	/* general purpose buffers */
> +	general_register_memory_regions(&vhost_memory, &region_idx);
> +
> +	/* tcp specific buffers */
> +	tcp_register_memory_regions(&vhost_memory, &region_idx);
> +
> +	/* udp specific buffers */
> +	udp_register_memory_regions(&vhost_memory, &region_idx);
> +
> +	vhost_memory.mem.nregions = region_idx;
> +
> +	return ioctl(c->vhost.fd, VHOST_SET_MEM_TABLE, &vhost_memory.mem);
> +}
> +
> +/**
> + * vhost_set_vring() - Register a vring's addresses and bind its backend
> + * @c:		Execution context; c->vhost.fd must already be set
> + * @queue_idx:	Index of the queue (vring) to configure
> + * @tap_fd:	Tap fd to bind as this queue's backend
> + */
> +void vhost_set_vring(struct ctx *c, int queue_idx, int tap_fd)
> +{
> +	int vhost_fd = c->vhost.fd;
> +	struct vhost_vring_addr addr = {
> +		.index = queue_idx,
> +		.desc_user_addr = (unsigned long)vring_desc[queue_idx],
> +		.avail_user_addr = (unsigned long)&vring_avail_all[queue_idx],
> +		.used_user_addr = (unsigned long)&vring_used_all[queue_idx],
> +		.log_guest_addr = (unsigned long)&vring_used_all[queue_idx],
> +	};
> +	struct vhost_vring_file file = {
> +		.index = queue_idx,
> +		.fd = tap_fd,
> +	};
> +	unsigned int i;
> +	int rc;
> +
> +	rc = ioctl(vhost_fd, VHOST_SET_VRING_ADDR, &addr);
> +	if (rc < 0)
> +		die_perror("VHOST_SET_VRING_ADDR ioctl failed, queue %d",
> +			   queue_idx);
> +
> +	if (queue_idx == VHOST_AVAIL_Q_IDX) {
> +		for (i = 0; i < VHOST_NDESCS; ++i) {
> +			vring_desc[VHOST_AVAIL_Q_IDX][i].addr =
> +				(uintptr_t)pkt_buf + i * VHOST_DESC_BYTES;
> +			vring_desc[VHOST_AVAIL_Q_IDX][i].len = VHOST_DESC_BYTES;
> +			vring_desc[VHOST_AVAIL_Q_IDX][i].flags =
> +				VRING_DESC_F_WRITE;

Missing endianness conversions.

> +		}
> +
> +		for (i = 0; i < VHOST_NDESCS; ++i)
> +			vring_avail_all[VHOST_AVAIL_Q_IDX].ring[i] =
> +				htole16(i);
> +
> +		vhost_rx_descriptor_handoff(c);
> +	}
> +
> +	if (queue_idx == VHOST_USED_Q_IDX) {
> +		for (i = 0; i < (VHOST_NDESCS - 1); ++i)
> +			vring_desc[VHOST_USED_Q_IDX][i].next = i + 1;

missing endianness conversion.

> +	}
> +
> +	rc = ioctl(vhost_fd, VHOST_NET_SET_BACKEND, &file);
> +	if (rc < 0)
> +		die_perror("VHOST_NET_SET_BACKEND ioctl failed, queue %d",
> +			   queue_idx);
> +}
> +
> +/**
> + * vhost_rx_descriptor_handoff() - Announce freed from-guest descriptors
> + * @c:		Execution context
> + *
> + * Bumps avail.idx by the number of descriptors accumulated in
> + * vhost_vq_state[VHOST_AVAIL_Q_IDX].num_free (from prior
> + * consume_one_rx_descriptor() calls),
> + * then resets the counter to zero. The kernel will see the new
> + * avail.idx and consume the freshly-available descriptors.
> + */
> +void vhost_rx_descriptor_handoff(struct ctx *c)

must be "const struct ctx *c"
  > +{
> +	smp_wmb();
> +
> +	if (!vhost_vq_state[VHOST_AVAIL_Q_IDX].num_free)
> +		return;
> +
> +	vring_avail_all[VHOST_AVAIL_Q_IDX].idx +=
> +		vhost_vq_state[VHOST_AVAIL_Q_IDX].num_free;
> +	vhost_vq_state[VHOST_AVAIL_Q_IDX].num_free = 0;
> +	vhost_kick(&vring_used_all[VHOST_AVAIL_Q_IDX],
> +		   c->vhost.vq[VHOST_AVAIL_Q_IDX].kick_fd);
> +}
> +
> +/**
> + * vhost_kick() - Notify the kernel that new descriptors are available
> + * @used:	Used ring of the queue we're announcing on, checked to see
> + *		whether the kernel's virtio thread is already reading
> + *		descriptors and doesn't want to be notified
> + * @kick_fd:	Kick eventfd of that same queue
> + */
> +void vhost_kick(struct vring_used_pasta *used, int kick_fd)

must be "const struct vring_used_pasta *"
> +{
> +	/* Ensure that the read of used->flags doesn't get reordered to be
> +	 * above the avail.idx update
> +	 */
> +	smp_mb();
> +
> +	if (!(used->flags & VRING_USED_F_NO_NOTIFY))
> +		eventfd_write(kick_fd, 1);
> +}
> diff --git a/vhost.h b/vhost.h
> new file mode 100644
> index 0000000..bd555f9
> --- /dev/null
> +++ b/vhost.h
> @@ -0,0 +1,91 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later
> + * Copyright Red Hat
> + * Author: Ammar Yasser <aerosound161@gmail.com>
> + *
> + * vhost.h - vhost-net (vhost-kernel) acceleration for pasta mode
> + */
> +
> +#ifndef VHOST_H
> +#define VHOST_H
> +
> +#include <assert.h>
> +#include <stddef.h>
> +#include <stdint.h>
> +
> +#include <linux/vhost.h>
> +#include <linux/vhost_types.h>
> +#include <linux/virtio_config.h>
> +#include <linux/virtio_net.h>
> +#include <linux/virtio_ring.h>
> +
> +#include "passt.h"
> +
> +#define VHOST_AVAIL_Q_IDX 0
> +#define VHOST_USED_Q_IDX 1
> +
> +/**
> + * struct vq_state - Per-virtqueue local descriptor tracking
> + * @num_free:		Number of descriptors ready to be announced to the
> + *			kernel via vhost_rx_descriptor_handoff()
> + * @last_used_idx:	Number of used-ring entries consumed so far;
> + *			lagging read cursor vs. vring_used->idx (the
> + *			kernel's write cursor)
> + */
> +extern struct vq_state {
> +	uint16_t num_free;
> +	uint16_t last_used_idx;
> +	uint16_t next_free;
> +} vhost_vq_state[2];
> +
> +struct vring_desc_pasta {

Why don't you use vring_desc from linux/virtio_ring.h

> +	__virtio64 addr;
> +	__virtio32 len;
> +	__virtio16 flags;
> +	__virtio16 next;
> +};
> +
> +extern struct vring_desc_pasta vring_desc[2][VHOST_NDESCS];
> +
> +struct vring_avail_pasta {
> +	__virtio16 flags;
> +	__virtio16 idx;
> +	__virtio16 ring[VHOST_NDESCS];
> +};
> +static_assert(sizeof(struct vring_avail_pasta) ==
> +	      offsetof(struct vring_avail, ring[VHOST_NDESCS]),
> +	      "vring_avail_pasta doesn't match the kernel avail ring layout");
> +extern struct vring_avail_pasta vring_avail_all[2];
> +
> +struct vring_used_pasta {
> +	__virtio16 flags;
> +	__virtio16 idx;
> +	vring_used_elem_t ring[VHOST_NDESCS];
> +};
> +static_assert(sizeof(struct vring_used_pasta) ==
> +	      offsetof(struct vring_used, ring[VHOST_NDESCS]),
> +	      "vring_used_pasta doesn't match the kernel used ring layout");
> +extern struct vring_used_pasta vring_used_all[2];
> +
> +#define N_VHOST_REGIONS 12
> +union vhost_memory_u {
> +	struct vhost_memory mem;
> +	char buf[offsetof(struct vhost_memory, regions[N_VHOST_REGIONS])];
> +};

struct vhost_memory_pasta {
     __u32 nregions;
     __u32 padding;
     struct vhost_memory_region regions[N_VHOST_REGIONS];
};

> +extern union vhost_memory_u vhost_memory;
> +
> +#define VHOST_MEMORY_REGION_PTR(addr, size) \
> +    (struct vhost_memory_region) { \
> +        .guest_phys_addr = (uintptr_t)addr, \
> +        .memory_size = size, \
> +        .userspace_addr  = (uintptr_t)addr, \
> +    }
> +#define VHOST_MEMORY_REGION(buf) VHOST_MEMORY_REGION_PTR(&buf, sizeof(buf))
> +
> +void vhost_set_vring(struct ctx *c, int queue_idx, int tap_fd);
> +int vhost_setup_memory_table(struct ctx *c);
> +int vhost_setup_net(struct ctx *c);
> +void vhost_setup_eventfds(struct ctx *c, int queue_idx);
> +void vhost_rx_descriptor_handoff(struct ctx *c);
> +void vhost_kick(struct vring_used_pasta *used, int kick_fd);
> +
> +#endif /* VHOST_H */
> --
> 2.39.5 (Apple Git-154)