freebsd-skq/sys/net/ieee8023ad_lacp.h
John Baldwin b2e60773c6 Add kernel-side support for in-kernel TLS.
KTLS adds support for in-kernel framing and encryption of Transport
Layer Security (1.0-1.2) data on TCP sockets.  KTLS only supports
offload of TLS for transmitted data.  Key negotation must still be
performed in userland.  Once completed, transmit session keys for a
connection are provided to the kernel via a new TCP_TXTLS_ENABLE
socket option.  All subsequent data transmitted on the socket is
placed into TLS frames and encrypted using the supplied keys.

Any data written to a KTLS-enabled socket via write(2), aio_write(2),
or sendfile(2) is assumed to be application data and is encoded in TLS
frames with an application data type.  Individual records can be sent
with a custom type (e.g. handshake messages) via sendmsg(2) with a new
control message (TLS_SET_RECORD_TYPE) specifying the record type.

At present, rekeying is not supported though the in-kernel framework
should support rekeying.

KTLS makes use of the recently added unmapped mbufs to store TLS
frames in the socket buffer.  Each TLS frame is described by a single
ext_pgs mbuf.  The ext_pgs structure contains the header of the TLS
record (and trailer for encrypted records) as well as references to
the associated TLS session.

KTLS supports two primary methods of encrypting TLS frames: software
TLS and ifnet TLS.

Software TLS marks mbufs holding socket data as not ready via
M_NOTREADY similar to sendfile(2) when TLS framing information is
added to an unmapped mbuf in ktls_frame().  ktls_enqueue() is then
called to schedule TLS frames for encryption.  In the case of
sendfile_iodone() calls ktls_enqueue() instead of pru_ready() leaving
the mbufs marked M_NOTREADY until encryption is completed.  For other
writes (vn_sendfile when pages are available, write(2), etc.), the
PRUS_NOTREADY is set when invoking pru_send() along with invoking
ktls_enqueue().

A pool of worker threads (the "KTLS" kernel process) encrypts TLS
frames queued via ktls_enqueue().  Each TLS frame is temporarily
mapped using the direct map and passed to a software encryption
backend to perform the actual encryption.

(Note: The use of PHYS_TO_DMAP could be replaced with sf_bufs if
someone wished to make this work on architectures without a direct
map.)

KTLS supports pluggable software encryption backends.  Internally,
Netflix uses proprietary pure-software backends.  This commit includes
a simple backend in a new ktls_ocf.ko module that uses the kernel's
OpenCrypto framework to provide AES-GCM encryption of TLS frames.  As
a result, software TLS is now a bit of a misnomer as it can make use
of hardware crypto accelerators.

Once software encryption has finished, the TLS frame mbufs are marked
ready via pru_ready().  At this point, the encrypted data appears as
regular payload to the TCP stack stored in unmapped mbufs.

ifnet TLS permits a NIC to offload the TLS encryption and TCP
segmentation.  In this mode, a new send tag type (IF_SND_TAG_TYPE_TLS)
is allocated on the interface a socket is routed over and associated
with a TLS session.  TLS records for a TLS session using ifnet TLS are
not marked M_NOTREADY but are passed down the stack unencrypted.  The
ip_output_send() and ip6_output_send() helper functions that apply
send tags to outbound IP packets verify that the send tag of the TLS
record matches the outbound interface.  If so, the packet is tagged
with the TLS send tag and sent to the interface.  The NIC device
driver must recognize packets with the TLS send tag and schedule them
for TLS encryption and TCP segmentation.  If the the outbound
interface does not match the interface in the TLS send tag, the packet
is dropped.  In addition, a task is scheduled to refresh the TLS send
tag for the TLS session.  If a new TLS send tag cannot be allocated,
the connection is dropped.  If a new TLS send tag is allocated,
however, subsequent packets will be tagged with the correct TLS send
tag.  (This latter case has been tested by configuring both ports of a
Chelsio T6 in a lagg and failing over from one port to another.  As
the connections migrated to the new port, new TLS send tags were
allocated for the new port and connections resumed without being
dropped.)

ifnet TLS can be enabled and disabled on supported network interfaces
via new '[-]txtls[46]' options to ifconfig(8).  ifnet TLS is supported
across both vlan devices and lagg interfaces using failover, lacp with
flowid enabled, or lacp with flowid enabled.

Applications may request the current KTLS mode of a connection via a
new TCP_TXTLS_MODE socket option.  They can also use this socket
option to toggle between software and ifnet TLS modes.

In addition, a testing tool is available in tools/tools/switch_tls.
This is modeled on tcpdrop and uses similar syntax.  However, instead
of dropping connections, -s is used to force KTLS connections to
switch to software TLS and -i is used to switch to ifnet TLS.

Various sysctls and counters are available under the kern.ipc.tls
sysctl node.  The kern.ipc.tls.enable node must be set to true to
enable KTLS (it is off by default).  The use of unmapped mbufs must
also be enabled via kern.ipc.mb_use_ext_pgs to enable KTLS.

KTLS is enabled via the KERN_TLS kernel option.

This patch is the culmination of years of work by several folks
including Scott Long and Randall Stewart for the original design and
implementation; Drew Gallatin for several optimizations including the
use of ext_pgs mbufs, the M_NOTREADY mechanism for TLS records
awaiting software encryption, and pluggable software crypto backends;
and John Baldwin for modifications to support hardware TLS offload.

Reviewed by:	gallatin, hselasky, rrs
Obtained from:	Netflix
Sponsored by:	Netflix, Chelsio Communications
Differential Revision:	https://reviews.freebsd.org/D21277
2019-08-27 00:01:56 +00:00

354 lines
9.2 KiB
C

/* $NetBSD: ieee8023ad_impl.h,v 1.2 2005/12/10 23:21:39 elad Exp $ */
/*-
* SPDX-License-Identifier: BSD-2-Clause-NetBSD
*
* Copyright (c)2005 YAMAMOTO Takashi,
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* $FreeBSD$
*/
/*
* IEEE802.3ad LACP
*
* implementation details.
*/
#define LACP_TIMER_CURRENT_WHILE 0
#define LACP_TIMER_PERIODIC 1
#define LACP_TIMER_WAIT_WHILE 2
#define LACP_NTIMER 3
#define LACP_TIMER_ARM(port, timer, val) \
(port)->lp_timer[(timer)] = (val)
#define LACP_TIMER_DISARM(port, timer) \
(port)->lp_timer[(timer)] = 0
#define LACP_TIMER_ISARMED(port, timer) \
((port)->lp_timer[(timer)] > 0)
/*
* IEEE802.3ad LACP
*
* protocol definitions.
*/
#define LACP_STATE_ACTIVITY (1<<0)
#define LACP_STATE_TIMEOUT (1<<1)
#define LACP_STATE_AGGREGATION (1<<2)
#define LACP_STATE_SYNC (1<<3)
#define LACP_STATE_COLLECTING (1<<4)
#define LACP_STATE_DISTRIBUTING (1<<5)
#define LACP_STATE_DEFAULTED (1<<6)
#define LACP_STATE_EXPIRED (1<<7)
#define LACP_PORT_NTT 0x00000001
#define LACP_PORT_MARK 0x00000002
#define LACP_STATE_BITS \
"\020" \
"\001ACTIVITY" \
"\002TIMEOUT" \
"\003AGGREGATION" \
"\004SYNC" \
"\005COLLECTING" \
"\006DISTRIBUTING" \
"\007DEFAULTED" \
"\010EXPIRED"
#ifdef _KERNEL
/*
* IEEE802.3 slow protocols
*
* protocol (on-wire) definitions.
*
* XXX should be elsewhere.
*/
#define SLOWPROTOCOLS_SUBTYPE_LACP 1
#define SLOWPROTOCOLS_SUBTYPE_MARKER 2
struct slowprothdr {
uint8_t sph_subtype;
uint8_t sph_version;
} __packed;
/*
* TLV on-wire structure.
*/
struct tlvhdr {
uint8_t tlv_type;
uint8_t tlv_length;
/* uint8_t tlv_value[]; */
} __packed;
/*
* ... and our implementation.
*/
#define TLV_SET(tlv, type, length) \
do { \
(tlv)->tlv_type = (type); \
(tlv)->tlv_length = sizeof(*tlv) + (length); \
} while (/*CONSTCOND*/0)
struct tlv_template {
uint8_t tmpl_type;
uint8_t tmpl_length;
};
struct lacp_systemid {
uint16_t lsi_prio;
uint8_t lsi_mac[6];
} __packed;
struct lacp_portid {
uint16_t lpi_prio;
uint16_t lpi_portno;
} __packed;
struct lacp_peerinfo {
struct lacp_systemid lip_systemid;
uint16_t lip_key;
struct lacp_portid lip_portid;
uint8_t lip_state;
uint8_t lip_resv[3];
} __packed;
struct lacp_collectorinfo {
uint16_t lci_maxdelay;
uint8_t lci_resv[12];
} __packed;
struct lacpdu {
struct ether_header ldu_eh;
struct slowprothdr ldu_sph;
struct tlvhdr ldu_tlv_actor;
struct lacp_peerinfo ldu_actor;
struct tlvhdr ldu_tlv_partner;
struct lacp_peerinfo ldu_partner;
struct tlvhdr ldu_tlv_collector;
struct lacp_collectorinfo ldu_collector;
struct tlvhdr ldu_tlv_term;
uint8_t ldu_resv[50];
} __packed;
/*
* IEEE802.3ad marker protocol
*
* protocol (on-wire) definitions.
*/
struct lacp_markerinfo {
uint16_t mi_rq_port;
uint8_t mi_rq_system[ETHER_ADDR_LEN];
uint32_t mi_rq_xid;
uint8_t mi_pad[2];
} __packed;
struct markerdu {
struct ether_header mdu_eh;
struct slowprothdr mdu_sph;
struct tlvhdr mdu_tlv;
struct lacp_markerinfo mdu_info;
struct tlvhdr mdu_tlv_term;
uint8_t mdu_resv[90];
} __packed;
#define MARKER_TYPE_INFO 0x01
#define MARKER_TYPE_RESPONSE 0x02
enum lacp_selected {
LACP_UNSELECTED,
LACP_STANDBY, /* not used in this implementation */
LACP_SELECTED,
};
enum lacp_mux_state {
LACP_MUX_DETACHED,
LACP_MUX_WAITING,
LACP_MUX_ATTACHED,
LACP_MUX_COLLECTING,
LACP_MUX_DISTRIBUTING,
};
#define LACP_MAX_PORTS 32
struct lacp_numa {
int count;
struct lacp_port *map[LACP_MAX_PORTS];
};
struct lacp_portmap {
int pm_count;
int pm_num_dom;
struct lacp_numa pm_numa[MAXMEMDOM];
struct lacp_port *pm_map[LACP_MAX_PORTS];
};
struct lacp_port {
TAILQ_ENTRY(lacp_port) lp_dist_q;
LIST_ENTRY(lacp_port) lp_next;
struct lacp_softc *lp_lsc;
struct lagg_port *lp_lagg;
struct ifnet *lp_ifp;
struct lacp_peerinfo lp_partner;
struct lacp_peerinfo lp_actor;
struct lacp_markerinfo lp_marker;
#define lp_state lp_actor.lip_state
#define lp_key lp_actor.lip_key
#define lp_systemid lp_actor.lip_systemid
struct timeval lp_last_lacpdu;
int lp_lacpdu_sent;
enum lacp_mux_state lp_mux_state;
enum lacp_selected lp_selected;
int lp_flags;
u_int lp_media; /* XXX redundant */
int lp_timer[LACP_NTIMER];
struct ifmultiaddr *lp_ifma;
struct lacp_aggregator *lp_aggregator;
};
struct lacp_aggregator {
TAILQ_ENTRY(lacp_aggregator) la_q;
int la_refcnt; /* num of ports which selected us */
int la_nports; /* num of distributing ports */
TAILQ_HEAD(, lacp_port) la_ports; /* distributing ports */
struct lacp_peerinfo la_partner;
struct lacp_peerinfo la_actor;
int la_pending; /* number of ports in wait_while */
};
struct lacp_softc {
struct lagg_softc *lsc_softc;
struct mtx lsc_mtx;
struct lacp_aggregator *lsc_active_aggregator;
TAILQ_HEAD(, lacp_aggregator) lsc_aggregators;
boolean_t lsc_suppress_distributing;
struct callout lsc_transit_callout;
struct callout lsc_callout;
LIST_HEAD(, lacp_port) lsc_ports;
struct lacp_portmap lsc_pmap[2];
volatile u_int lsc_activemap;
u_int32_t lsc_hashkey;
struct {
u_int32_t lsc_rx_test;
u_int32_t lsc_tx_test;
} lsc_debug;
u_int32_t lsc_strict_mode;
boolean_t lsc_fast_timeout; /* if set, fast timeout */
};
#define LACP_TYPE_ACTORINFO 1
#define LACP_TYPE_PARTNERINFO 2
#define LACP_TYPE_COLLECTORINFO 3
/* timeout values (in sec) */
#define LACP_FAST_PERIODIC_TIME (1)
#define LACP_SLOW_PERIODIC_TIME (30)
#define LACP_SHORT_TIMEOUT_TIME (3 * LACP_FAST_PERIODIC_TIME)
#define LACP_LONG_TIMEOUT_TIME (3 * LACP_SLOW_PERIODIC_TIME)
#define LACP_CHURN_DETECTION_TIME (60)
#define LACP_AGGREGATE_WAIT_TIME (2)
#define LACP_TRANSIT_DELAY 3000 /* in msec */
#define LACP_STATE_EQ(s1, s2, mask) \
((((s1) ^ (s2)) & (mask)) == 0)
#define LACP_SYS_PRI(peer) (peer).lip_systemid.lsi_prio
#define LACP_PORT(_lp) ((struct lacp_port *)(_lp)->lp_psc)
#define LACP_SOFTC(_sc) ((struct lacp_softc *)(_sc)->sc_psc)
#define LACP_LOCK_INIT(_lsc) mtx_init(&(_lsc)->lsc_mtx, \
"lacp mtx", NULL, MTX_DEF)
#define LACP_LOCK_DESTROY(_lsc) mtx_destroy(&(_lsc)->lsc_mtx)
#define LACP_LOCK(_lsc) mtx_lock(&(_lsc)->lsc_mtx)
#define LACP_UNLOCK(_lsc) mtx_unlock(&(_lsc)->lsc_mtx)
#define LACP_LOCK_ASSERT(_lsc) mtx_assert(&(_lsc)->lsc_mtx, MA_OWNED)
struct mbuf *lacp_input(struct lagg_port *, struct mbuf *);
struct lagg_port *lacp_select_tx_port(struct lagg_softc *, struct mbuf *);
#if defined(RATELIMIT) || defined(KERN_TLS)
struct lagg_port *lacp_select_tx_port_by_hash(struct lagg_softc *, uint32_t);
#endif
void lacp_attach(struct lagg_softc *);
void lacp_detach(void *);
void lacp_init(struct lagg_softc *);
void lacp_stop(struct lagg_softc *);
int lacp_port_create(struct lagg_port *);
void lacp_port_destroy(struct lagg_port *);
void lacp_linkstate(struct lagg_port *);
void lacp_req(struct lagg_softc *, void *);
void lacp_portreq(struct lagg_port *, void *);
static __inline int
lacp_isactive(struct lagg_port *lgp)
{
struct lacp_port *lp = LACP_PORT(lgp);
struct lacp_softc *lsc = lp->lp_lsc;
struct lacp_aggregator *la = lp->lp_aggregator;
/* This port is joined to the active aggregator */
if (la != NULL && la == lsc->lsc_active_aggregator)
return (1);
return (0);
}
static __inline int
lacp_iscollecting(struct lagg_port *lgp)
{
struct lacp_port *lp = LACP_PORT(lgp);
return ((lp->lp_state & LACP_STATE_COLLECTING) != 0);
}
static __inline int
lacp_isdistributing(struct lagg_port *lgp)
{
struct lacp_port *lp = LACP_PORT(lgp);
return ((lp->lp_state & LACP_STATE_DISTRIBUTING) != 0);
}
/* following constants don't include terminating NUL */
#define LACP_MACSTR_MAX (2*6 + 5)
#define LACP_SYSTEMPRIOSTR_MAX (4)
#define LACP_SYSTEMIDSTR_MAX (LACP_SYSTEMPRIOSTR_MAX + 1 + LACP_MACSTR_MAX)
#define LACP_PORTPRIOSTR_MAX (4)
#define LACP_PORTNOSTR_MAX (4)
#define LACP_PORTIDSTR_MAX (LACP_PORTPRIOSTR_MAX + 1 + LACP_PORTNOSTR_MAX)
#define LACP_KEYSTR_MAX (4)
#define LACP_PARTNERSTR_MAX \
(1 + LACP_SYSTEMIDSTR_MAX + 1 + LACP_KEYSTR_MAX + 1 \
+ LACP_PORTIDSTR_MAX + 1)
#define LACP_LAGIDSTR_MAX \
(1 + LACP_PARTNERSTR_MAX + 1 + LACP_PARTNERSTR_MAX + 1)
#define LACP_STATESTR_MAX (255) /* XXX */
#endif /* _KERNEL */