// SPDX-License-Identifier: GPL-2.0-or-later

/* PASST - Plug A Simple Socket Transport
 *  for qemu/UNIX domain socket mode
 *
 * PASTA - Pack A Subtle Tap Abstraction
 *  for network namespace/tap device mode
 *
 * migrate.c - Migration sections, layout, and routines
 *
 * Copyright (c) 2025 Red Hat GmbH
 * Author: Stefano Brivio <sbrivio@redhat.com>
 */

#include <errno.h>
#include <sys/uio.h>

#include "util.h"
#include "ip.h"
#include "passt.h"
#include "inany.h"
#include "flow.h"
#include "flow_table.h"
#include "repair.h"

#include "migrate.h"

/* Current version of migration data */
#define MIGRATE_VERSION		1

/* Magic identifier for migration data */
#define MIGRATE_MAGIC		0xB1BB1D1B0BB1D1B0

/* Migration header to send from source */
static struct migrate_header header = {
	.magic		= htonll_constant(MIGRATE_MAGIC),
	.version	= htonl_constant(MIGRATE_VERSION),
};

/**
 * migrate_send_block() - Migration stage handler to send verbatim data
 * @c:		Execution context
 * @stage:	Migration stage
 * @fd:		Migration fd
 *
 * Sends the buffer in @stage->iov over the migration channel.
 */
__attribute__((__unused__))
static int migrate_send_block(struct ctx *c,
			      const struct migrate_stage *stage, int fd)
{
	(void)c;

	if (write_remainder(fd, &stage->iov, 1, 0) < 0)
		return errno;

	return 0;
}

/**
 * migrate_recv_block() - Migration stage handler to receive verbatim data
 * @c:		Execution context
 * @stage:	Migration stage
 * @fd:		Migration fd
 *
 * Reads the buffer in @stage->iov from the migration channel.
 *
 * #syscalls:vu readv
 */
__attribute__((__unused__))
static int migrate_recv_block(struct ctx *c,
			      const struct migrate_stage *stage, int fd)
{
	(void)c;

	if (read_remainder(fd, &stage->iov, 1, 0) < 0)
		return errno;

	return 0;
}

#define DATA_STAGE(v) \
	{					\
		.name = #v,			\
		.source = migrate_send_block,	\
		.target = migrate_recv_block,	\
		.iov = { &(v), sizeof(v) },	\
	}

/* Stages for version 1 */
static const struct migrate_stage stages_v1[] = {
	{
		.name = "flow pre",
		.target = NULL,
	},
	{
		.name = "flow post",
		.source = NULL,
	},
	{ 0 },
};

/* Set of data versions */
static const struct migrate_version versions[] = {
	{
		1,	stages_v1,
	},
	{ 0 },
};

/**
 * migrate_source() - Migration as source, send state to hypervisor
 * @c:		Execution context
 * @fd:		File descriptor for state transfer
 *
 * Return: 0 on success, positive error code on failure
 */
static int migrate_source(struct ctx *c, int fd)
{
	const struct migrate_version *v = versions + ARRAY_SIZE(versions) - 1;
	const struct migrate_stage *s;
	int ret;

	ret = write_all_buf(fd, &header, sizeof(header));
	if (ret) {
		err("Can't send migration header: %s, abort", strerror_(ret));
		return ret;
	}

	for (s = v->s; *s->name; s++) {
		if (!s->source)
			continue;

		debug("Source side migration: %s", s->name);

		if ((ret = s->source(c, s, fd))) {
			err("Source migration stage %s: %s, abort", s->name,
			    strerror_(ret));
			return ret;
		}
	}

	return 0;
}

/**
 * migrate_target_read_header() - Read header in target
 * @fd:		Descriptor for state transfer
 *
 * Return: version number on success, 0 on failure with errno set
 */
static uint32_t migrate_target_read_header(int fd)
{
	struct migrate_header h;

	if (read_all_buf(fd, &h, sizeof(h)))
		return 0;

	debug("Source magic: 0x%016" PRIx64 ", version: %u",
	      be64toh(h.magic), ntohl_constant(h.version));

	if (ntohll_constant(h.magic) != MIGRATE_MAGIC || !ntohl(h.version)) {
		errno = EINVAL;
		return 0;
	}

	return ntohl(h.version);
}

/**
 * migrate_target() - Migration as target, receive state from hypervisor
 * @c:		Execution context
 * @fd:		File descriptor for state transfer
 *
 * Return: 0 on success, positive error code on failure
 */
static int migrate_target(struct ctx *c, int fd)
{
	const struct migrate_version *v;
	const struct migrate_stage *s;
	uint32_t id;
	int ret;

	id = migrate_target_read_header(fd);
	if (!id) {
		ret = errno;
		err("Migration header check failed: %s, abort", strerror_(ret));
		return ret;
	}

	for (v = versions; v->id && v->id == id; v++);
	if (!v->id) {
		err("Unsupported version: %u", id);
		return -ENOTSUP;
	}

	for (s = v->s; *s->name; s++) {
		if (!s->target)
			continue;

		debug("Target side migration: %s", s->name);

		if ((ret = s->target(c, s, fd))) {
			err("Target migration stage %s: %s, abort", s->name,
			    strerror_(ret));
			return ret;
		}
	}

	return 0;
}

/**
 * set_migration_watch() - Add the migration file descriptor to epoll
 * @c:		Execution context
 * @fd:		File descriptor to add
 * @target:	Are we the target of the migration?
 */
static void set_migration_watch(const struct ctx *c, int fd, bool target)
{
	union epoll_ref ref = {
		.type = EPOLL_TYPE_DEVICE_STATE,
		.fd = fd,
	 };
	struct epoll_event ev = { 0 };

	ev.data.u64 = ref.u64;
	ev.events = target ? EPOLLIN : EPOLLOUT;

	epoll_ctl(c->epollfd, EPOLL_CTL_ADD, ref.fd, &ev);
}

/**
 * migrate_init() - Set up things necessary for migration
 * @c:		Execution context
 */
void migrate_init(struct ctx *c)
{
	c->device_state_fd = -1;
	c->device_state_result = -1;
}

/**
 * migrate_close() - Close migration channel
 * @c:		Execution context
 */
void migrate_close(struct ctx *c)
{
	if (c->device_state_fd != -1) {
		debug("Closing migration channel, fd: %d", c->device_state_fd);
		epoll_del(c, c->device_state_fd);
		close(c->device_state_fd);
		c->device_state_fd = -1;
		c->device_state_result = -1;
	}
}

/**
 * migrate_request() - Request a migration of device state
 * @c:		Execution context
 * @fd:		fd to transfer state
 * @target:	Are we the target of the migration?
 */
void migrate_request(struct ctx *c, int fd, bool target)
{
	debug("Migration requested, fd: %d (was %d)",
	      fd, c->device_state_fd);

	if (c->device_state_fd != -1)
		migrate_close(c);

	c->device_state_fd = fd;
	set_migration_watch(c, c->device_state_fd, target);

}

/**
 * migrate_handler() - Send/receive passt internal state to/from QEMU
 * @c:		Execution context
 * @events:	epoll events
 */
void migrate_handler(struct ctx *c, uint32_t events)
{
	int rc = EIO;

	debug("migrate_handler fd %d events %x", c->device_state_fd, events);

	if (events & EPOLLOUT)
		rc = migrate_source(c, c->device_state_fd);
	else if (events & EPOLLIN)
		rc = migrate_target(c, c->device_state_fd);

	/* EPOLLHUP without EPOLLIN/EPOLLOUT, or EPOLLERR? Migration failed */

	migrate_close(c);

	c->device_state_result = rc;
}