// 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 "conf.h"
#include "fwd.h"
#include "inany.h"
#include "flow.h"
#include "flow_table.h"

#include "migrate.h"
#include "repair.h"

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

/**
 * struct migrate_seen_addrs_v2 - Migratable guest addresses for v2 state stream
 * @addr6:	Observed guest IPv6 address
 * @addr6_ll:	Observed guest IPv6 link-local address
 * @addr4:	Observed guest IPv4 address
 * @mac:	Observed guest MAC address
 */
struct migrate_seen_addrs_v2 {
	struct in6_addr addr6;
	struct in6_addr addr6_ll;
	struct in_addr addr4;
	unsigned char mac[ETH_ALEN];
} __attribute__((packed));

/**
 * Wire format flags for address migration (v3)
 * These are stable values - do not change existing assignments
 */
#define MIGRATE_ADDR_USER	BIT(0)
#define MIGRATE_ADDR_HOST	BIT(1)
#define MIGRATE_ADDR_LINKLOCAL	BIT(2)
#define MIGRATE_ADDR_OBSERVED	BIT(3)
#define MIGRATE_ADDR_DHCP	BIT(4)
#define MIGRATE_ADDR_DHCPV6	BIT(5)
#define MIGRATE_ADDR_NDP	BIT(6)

/**
 * struct migrate_addr_v3 - Wire format for a single address entry
 * @addr:	IPv6 or IPv4-mapped address (16 bytes)
 * @prefix_len:	Prefix length
 * @flags:	MIGRATE_ADDR_* flags (wire format)
 */
struct migrate_addr_v3 {
	struct in6_addr addr;
	uint8_t prefix_len;
	uint8_t flags;
} __attribute__((__packed__));

/**
 * flags_to_wire() - Convert internal flags to stable wire format
 * @flags:	Internal CONF_ADDR_* flags
 *
 * Return: Wire format MIGRATE_ADDR_* flags
 */
static uint8_t flags_to_wire(uint8_t flags)
{
	uint8_t wire = 0;

	if (flags & CONF_ADDR_USER)
		wire |= MIGRATE_ADDR_USER;
	if (flags & CONF_ADDR_HOST)
		wire |= MIGRATE_ADDR_HOST;
	if (flags & CONF_ADDR_LINKLOCAL)
		wire |= MIGRATE_ADDR_LINKLOCAL;
	if (flags & CONF_ADDR_OBSERVED)
		wire |= MIGRATE_ADDR_OBSERVED;
	if (flags & CONF_ADDR_DHCP)
		wire |= MIGRATE_ADDR_DHCP;
	if (flags & CONF_ADDR_DHCPV6)
		wire |= MIGRATE_ADDR_DHCPV6;
	if (flags & CONF_ADDR_NDP)
		wire |= MIGRATE_ADDR_NDP;

	return wire;
}

/**
 * flags_from_wire() - Convert wire format flags to internal format
 * @wire:	Wire format MIGRATE_ADDR_* flags
 *
 * Return: Internal CONF_ADDR_* flags
 */
static uint8_t flags_from_wire(uint8_t wire)
{
	uint8_t flags = 0;

	if (wire & MIGRATE_ADDR_USER)
		flags |= CONF_ADDR_USER;
	if (wire & MIGRATE_ADDR_HOST)
		flags |= CONF_ADDR_HOST;
	if (wire & MIGRATE_ADDR_LINKLOCAL)
		flags |= CONF_ADDR_LINKLOCAL;
	if (wire & MIGRATE_ADDR_OBSERVED)
		flags |= CONF_ADDR_OBSERVED;
	if (wire & MIGRATE_ADDR_DHCP)
		flags |= CONF_ADDR_DHCP;
	if (wire & MIGRATE_ADDR_DHCPV6)
		flags |= CONF_ADDR_DHCPV6;
	if (wire & MIGRATE_ADDR_NDP)
		flags |= CONF_ADDR_NDP;

	return flags;
}

/**
 * seen_addrs_source_v2() - Copy and send guest observed addresses from source
 * @c:		Execution context
 * @stage:	Migration stage, unused
 * @fd:		File descriptor for state transfer
 *
 * Return: 0 on success, positive error code on failure
 */
/* cppcheck-suppress [constParameterCallback, unmatchedSuppression] */
static int seen_addrs_source_v2(struct ctx *c,
				const struct migrate_stage *stage, int fd)
{
	struct migrate_seen_addrs_v2 addrs = { 0 };
	const struct guest_addr *a;

	(void)stage;

	/* IPv4 observed address, with fallback to any other non-LL address */
	a = fwd_select_addr(c, AF_INET, CONF_ADDR_OBSERVED,
			    CONF_ADDR_USER | CONF_ADDR_HOST,
			    CONF_ADDR_LINKLOCAL);
	if (a)
		addrs.addr4 = *inany_v4(&a->addr);

	/* IPv6 observed address, with fallback to any other non-LL address */
	a = fwd_select_addr(c, AF_INET6, CONF_ADDR_OBSERVED,
			    CONF_ADDR_USER | CONF_ADDR_HOST,
			    CONF_ADDR_LINKLOCAL);
	if (a)
		addrs.addr6 = a->addr.a6;

	/* IPv6 link-local address */
	a = fwd_get_addr(c, AF_INET6, CONF_ADDR_LINKLOCAL, 0);
	if (a)
		addrs.addr6_ll = a->addr.a6;

	memcpy(addrs.mac, c->guest_mac, sizeof(addrs.mac));

	if (write_all_buf(fd, &addrs, sizeof(addrs)))
		return errno;

	return 0;
}

/**
 * seen_addrs_target_v2() - Receive and use guest observed addresses on target
 * @c:		Execution context
 * @stage:	Migration stage, unused
 * @fd:		File descriptor for state transfer
 *
 * Return: 0 on success, positive error code on failure
 */
static int seen_addrs_target_v2(struct ctx *c,
				const struct migrate_stage *stage, int fd)
{
	struct migrate_seen_addrs_v2 addrs;
	struct in6_addr addr6, addr6_ll;

	(void)stage;

	if (read_all_buf(fd, &addrs, sizeof(addrs)))
		return errno;

	if (addrs.addr4.s_addr)
		fwd_set_addr(c, &inany_from_v4(addrs.addr4),
			     CONF_ADDR_OBSERVED, 0);

	addr6 = addrs.addr6;
	if (!IN6_IS_ADDR_UNSPECIFIED(&addr6))
		fwd_set_addr(c, &inany_from_v6(addr6),
			     CONF_ADDR_OBSERVED, 0);

	addr6_ll = addrs.addr6_ll;
	if (!IN6_IS_ADDR_UNSPECIFIED(&addr6_ll))
		fwd_set_addr(c, &inany_from_v6(addr6_ll),
			     CONF_ADDR_OBSERVED | CONF_ADDR_LINKLOCAL, 0);

	memcpy(c->guest_mac, addrs.mac, sizeof(c->guest_mac));

	return 0;
}

/**
 * addrs_source_v3() - Send all addresses with flags from source
 * @c:		Execution context
 * @stage:	Migration stage, unused
 * @fd:		File descriptor for state transfer
 *
 * Send all address entries using a stable wire format. Each field is
 * serialized explicitly to avoid coupling the wire format to internal
 * structure layout or flag bit assignments.
 *
 * Return: 0 on success, positive error code on failure
 */
/* cppcheck-suppress [constParameterCallback, unmatchedSuppression] */
static int addrs_source_v3(struct ctx *c,
			   const struct migrate_stage *stage, int fd)
{
	uint8_t addr_count = c->addr_count;
	const struct guest_addr *a;

	(void)stage;

	/* Send count first */
	if (write_all_buf(fd, &addr_count, sizeof(addr_count)))
		return errno;

	/* Send each address in stable wire format */
	for_each_addr(a, c, 0) {
		struct migrate_addr_v3 wire = {
			.addr = a->addr.a6,
			.prefix_len = a->prefix_len,
			.flags = flags_to_wire(a->flags),
		};

		if (write_all_buf(fd, &wire, sizeof(wire)))
			return errno;
	}

	/* Send MAC */
	if (write_all_buf(fd, c->guest_mac, ETH_ALEN))
		return errno;

	return 0;
}

/**
 * addrs_target_v3() - Receive addresses on target
 * @c:		Execution context
 * @stage:	Migration stage, unused
 * @fd:		File descriptor for state transfer
 *
 * Receive address entries from the stable wire format and merge only
 * observed addresses into local array. Source sends all addresses for
 * forward compatibility, but target only applies those marked as observed.
 *
 * Return: 0 on success, positive error code on failure
 */
static int addrs_target_v3(struct ctx *c,
			   const struct migrate_stage *stage, int fd)
{
	uint8_t addr_count, i;

	(void)stage;

	if (read_all_buf(fd, &addr_count, sizeof(addr_count)))
		return errno;

	if (addr_count > MAX_GUEST_ADDRS)
		addr_count = MAX_GUEST_ADDRS;

	/* Read each address from stable wire format */
	for (i = 0; i < addr_count; i++) {
		struct migrate_addr_v3 wire;
		struct guest_addr addr;

		if (read_all_buf(fd, &wire, sizeof(wire)))
			return errno;

		addr.addr.a6 = wire.addr;
		addr.prefix_len = wire.prefix_len;
		addr.flags = flags_from_wire(wire.flags);

		if (addr.flags & CONF_ADDR_OBSERVED)
			fwd_set_addr(c, &addr.addr, addr.flags,
				     addr.prefix_len);
	}

	if (read_all_buf(fd, c->guest_mac, ETH_ALEN))
		return errno;

	return 0;
}

/* Stages for version 2 */
static const struct migrate_stage stages_v2[] = {
	{
		.name = "observed addresses",
		.source = seen_addrs_source_v2,
		.target = seen_addrs_target_v2,
	},
	{
		.name = "prepare flows",
		.source = flow_migrate_source_pre,
		.target = NULL,
	},
	{
		.name = "transfer flows",
		.source = flow_migrate_source,
		.target = flow_migrate_target,
	},
	{ 0 },
};

/* Stages for version 3 (multiple observed IPv4 addresses) */
static const struct migrate_stage stages_v3[] = {
	{
		.name = "addresses",
		.source = addrs_source_v3,
		.target = addrs_target_v3,
	},
	{
		.name = "prepare flows",
		.source = flow_migrate_source_pre,
		.target = NULL,
	},
	{
		.name = "transfer flows",
		.source = flow_migrate_source,
		.target = flow_migrate_target,
	},
	{ 0 },
};

/* Supported encoding versions, from latest (most preferred) to oldest */
static const struct migrate_version versions[] = {
	{ 3,	stages_v3, },
	{ 2,	stages_v2, },
	/* v1 was released, but not widely used.  It had bad endianness for the
	 * MSS and omitted timestamps, which meant it usually wouldn't work.
	 * Therefore we don't attempt to support compatibility with it.
	 */
};

/* Current encoding version */
#define CURRENT_VERSION		(&versions[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 = CURRENT_VERSION;
	const struct migrate_header header = {
		.magic		= htonll_constant(MIGRATE_MAGIC),
		.version	= htonl(v->id),
		.compat_version	= htonl(v->id),
	};
	const struct migrate_stage *s;
	int ret;

	if (write_all_buf(fd, &header, sizeof(header))) {
		ret = errno;
		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 stage: %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 structure on success, NULL on failure with errno set
 */
static const struct migrate_version *migrate_target_read_header(int fd)
{
	struct migrate_header h;
	uint32_t id, compat_id;
	unsigned i;

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

	id = ntohl(h.version);
	compat_id = ntohl(h.compat_version);

	debug("Source magic: 0x%016" PRIx64 ", version: %u, compat: %u",
	      ntohll(h.magic), id, compat_id);

	if (ntohll(h.magic) != MIGRATE_MAGIC || !id || !compat_id) {
		err("Invalid incoming device state");
		errno = EINVAL;
		return NULL;
	}

	for (i = 0; i < ARRAY_SIZE(versions); i++)
		if (versions[i].id <= id && versions[i].id >= compat_id)
			return &versions[i];

	errno = ENOTSUP;
	err("Unsupported device state version: %u", id);
	return NULL;
}

/**
 * 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;
	int ret;

	if (!(v = migrate_target_read_header(fd)))
		return errno;

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

		debug("Target side migration stage: %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;
}

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

/**
 * migrate_close() - Close migration channel and connection to passt-repair
 * @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);
		close(c->device_state_fd);
		c->device_state_fd = -1;
		c->device_state_result = -1;
	}

	repair_close(c);
}

/**
 * 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;
	c->migrate_target = target;
}

/**
 * migrate_handler() - Send/receive passt internal state to/from hypervisor
 * @c:		Execution context
 */
void migrate_handler(struct ctx *c)
{
	int rc;

	if (c->device_state_fd < 0)
		return;

	debug("Handling migration request from fd: %d, target: %d",
	      c->device_state_fd, c->migrate_target);

	if (c->migrate_target)
		rc = migrate_target(c, c->device_state_fd);
	else
		rc = migrate_source(c, c->device_state_fd);

	migrate_close(c);

	c->device_state_result = rc;
}