Blame view
net/sched/sch_etf.c
11.7 KB
25db26a91 net/sched: Introd... |
1 2 3 4 5 6 7 8 9 10 11 12 13 |
// SPDX-License-Identifier: GPL-2.0 /* net/sched/sch_etf.c Earliest TxTime First queueing discipline. * * Authors: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com> * Vinicius Costa Gomes <vinicius.gomes@intel.com> */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> |
4b15c7075 net/sched: Make e... |
14 |
#include <linux/errqueue.h> |
25db26a91 net/sched: Introd... |
15 16 17 18 19 20 21 22 23 |
#include <linux/rbtree.h> #include <linux/skbuff.h> #include <linux/posix-timers.h> #include <net/netlink.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/sock.h> #define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON) |
88cab7716 net/sched: Add HW... |
24 |
#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON) |
d14d2b206 etf: Add skip_soc... |
25 |
#define SKIP_SOCK_CHECK_IS_SET(x) ((x)->flags & TC_ETF_SKIP_SOCK_CHECK) |
25db26a91 net/sched: Introd... |
26 27 |
struct etf_sched_data { |
88cab7716 net/sched: Add HW... |
28 |
bool offload; |
25db26a91 net/sched: Introd... |
29 |
bool deadline_mode; |
d14d2b206 etf: Add skip_soc... |
30 |
bool skip_sock_check; |
25db26a91 net/sched: Introd... |
31 32 33 34 |
int clockid; int queue; s32 delta; /* in ns */ ktime_t last; /* The txtime of the last skb sent to the netdevice. */ |
09fd4860e etf: Use cached r... |
35 |
struct rb_root_cached head; |
25db26a91 net/sched: Introd... |
36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
struct qdisc_watchdog watchdog; ktime_t (*get_time)(void); }; static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = { [TCA_ETF_PARMS] = { .len = sizeof(struct tc_etf_qopt) }, }; static inline int validate_input_params(struct tc_etf_qopt *qopt, struct netlink_ext_ack *extack) { /* Check if params comply to the following rules: * * Clockid and delta must be valid. * * * Dynamic clockids are not supported. * * * Delta must be a positive integer. |
88cab7716 net/sched: Add HW... |
53 54 55 |
* * Also note that for the HW offload case, we must * expect that system clocks have been synchronized to PHC. |
25db26a91 net/sched: Introd... |
56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
*/ if (qopt->clockid < 0) { NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported"); return -ENOTSUPP; } if (qopt->clockid != CLOCK_TAI) { NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used"); return -EINVAL; } if (qopt->delta < 0) { NL_SET_ERR_MSG(extack, "Delta must be positive"); return -EINVAL; } return 0; } static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb) { struct etf_sched_data *q = qdisc_priv(sch); ktime_t txtime = nskb->tstamp; struct sock *sk = nskb->sk; ktime_t now; |
d14d2b206 etf: Add skip_soc... |
81 82 |
if (q->skip_sock_check) goto skip; |
a1211bf9a sched: etf: do no... |
83 |
if (!sk || !sk_fullsock(sk)) |
25db26a91 net/sched: Introd... |
84 85 86 87 88 89 90 91 92 93 94 95 96 |
return false; if (!sock_flag(sk, SOCK_TXTIME)) return false; /* We don't perform crosstimestamping. * Drop if packet's clockid differs from qdisc's. */ if (sk->sk_clockid != q->clockid) return false; if (sk->sk_txtime_deadline_mode != q->deadline_mode) return false; |
d14d2b206 etf: Add skip_soc... |
97 |
skip: |
25db26a91 net/sched: Introd... |
98 99 100 101 102 103 104 105 106 107 108 |
now = q->get_time(); if (ktime_before(txtime, now) || ktime_before(txtime, q->last)) return false; return true; } static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct rb_node *p; |
09fd4860e etf: Use cached r... |
109 |
p = rb_first_cached(&q->head); |
25db26a91 net/sched: Introd... |
110 111 112 113 114 115 116 117 118 119 120 |
if (!p) return NULL; return rb_to_skb(p); } static void reset_watchdog(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct sk_buff *skb = etf_peek_timesortedlist(sch); ktime_t next; |
3fcbdaee3 etf: Cancel timer... |
121 122 |
if (!skb) { qdisc_watchdog_cancel(&q->watchdog); |
25db26a91 net/sched: Introd... |
123 |
return; |
3fcbdaee3 etf: Cancel timer... |
124 |
} |
25db26a91 net/sched: Introd... |
125 126 127 128 |
next = ktime_sub_ns(skb->tstamp, q->delta); qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next)); } |
4b15c7075 net/sched: Make e... |
129 130 131 132 133 |
static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) { struct sock_exterr_skb *serr; struct sk_buff *clone; ktime_t txtime = skb->tstamp; |
a1211bf9a sched: etf: do no... |
134 |
struct sock *sk = skb->sk; |
4b15c7075 net/sched: Make e... |
135 |
|
a1211bf9a sched: etf: do no... |
136 |
if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors)) |
4b15c7075 net/sched: Make e... |
137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
return; clone = skb_clone(skb, GFP_ATOMIC); if (!clone) return; serr = SKB_EXT_ERR(clone); serr->ee.ee_errno = err; serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME; serr->ee.ee_type = 0; serr->ee.ee_code = code; serr->ee.ee_pad = 0; serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */ serr->ee.ee_info = txtime; /* low part of tstamp */ |
a1211bf9a sched: etf: do no... |
151 |
if (sock_queue_err_skb(sk, clone)) |
4b15c7075 net/sched: Make e... |
152 153 |
kfree_skb(clone); } |
25db26a91 net/sched: Introd... |
154 155 156 157 |
static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch, struct sk_buff **to_free) { struct etf_sched_data *q = qdisc_priv(sch); |
09fd4860e etf: Use cached r... |
158 |
struct rb_node **p = &q->head.rb_root.rb_node, *parent = NULL; |
25db26a91 net/sched: Introd... |
159 |
ktime_t txtime = nskb->tstamp; |
09fd4860e etf: Use cached r... |
160 |
bool leftmost = true; |
25db26a91 net/sched: Introd... |
161 |
|
4b15c7075 net/sched: Make e... |
162 163 164 |
if (!is_packet_valid(sch, nskb)) { report_sock_error(nskb, EINVAL, SO_EE_CODE_TXTIME_INVALID_PARAM); |
25db26a91 net/sched: Introd... |
165 |
return qdisc_drop(nskb, sch, to_free); |
4b15c7075 net/sched: Make e... |
166 |
} |
25db26a91 net/sched: Introd... |
167 168 169 170 171 172 |
while (*p) { struct sk_buff *skb; parent = *p; skb = rb_to_skb(parent); |
28aa7c86c sched: etf: Fix o... |
173 |
if (ktime_compare(txtime, skb->tstamp) >= 0) { |
25db26a91 net/sched: Introd... |
174 |
p = &parent->rb_right; |
09fd4860e etf: Use cached r... |
175 176 |
leftmost = false; } else { |
25db26a91 net/sched: Introd... |
177 |
p = &parent->rb_left; |
09fd4860e etf: Use cached r... |
178 |
} |
25db26a91 net/sched: Introd... |
179 180 |
} rb_link_node(&nskb->rbnode, parent, p); |
09fd4860e etf: Use cached r... |
181 |
rb_insert_color_cached(&nskb->rbnode, &q->head, leftmost); |
25db26a91 net/sched: Introd... |
182 183 184 185 186 187 188 189 190 |
qdisc_qstats_backlog_inc(sch, nskb); sch->q.qlen++; /* Now we may need to re-arm the qdisc watchdog for the next packet. */ reset_watchdog(sch); return NET_XMIT_SUCCESS; } |
37342bdaf etf: Drop all exp... |
191 192 |
static void timesortedlist_drop(struct Qdisc *sch, struct sk_buff *skb, ktime_t now) |
25db26a91 net/sched: Introd... |
193 194 |
{ struct etf_sched_data *q = qdisc_priv(sch); |
cbeeb8efe etf: Split timers... |
195 |
struct sk_buff *to_free = NULL; |
37342bdaf etf: Drop all exp... |
196 |
struct sk_buff *tmp = NULL; |
25db26a91 net/sched: Introd... |
197 |
|
37342bdaf etf: Drop all exp... |
198 199 200 |
skb_rbtree_walk_from_safe(skb, tmp) { if (ktime_after(skb->tstamp, now)) break; |
25db26a91 net/sched: Introd... |
201 |
|
37342bdaf etf: Drop all exp... |
202 |
rb_erase_cached(&skb->rbnode, &q->head); |
25db26a91 net/sched: Introd... |
203 |
|
37342bdaf etf: Drop all exp... |
204 205 206 207 208 209 |
/* The rbnode field in the skb re-uses these fields, now that * we are done with the rbnode, reset them. */ skb->next = NULL; skb->prev = NULL; skb->dev = qdisc_dev(sch); |
25db26a91 net/sched: Introd... |
210 |
|
37342bdaf etf: Drop all exp... |
211 |
report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED); |
25db26a91 net/sched: Introd... |
212 |
|
37342bdaf etf: Drop all exp... |
213 214 215 216 217 |
qdisc_qstats_backlog_dec(sch, skb); qdisc_drop(skb, sch, &to_free); qdisc_qstats_overlimit(sch); sch->q.qlen--; } |
4b15c7075 net/sched: Make e... |
218 |
|
37342bdaf etf: Drop all exp... |
219 |
kfree_skb_list(to_free); |
cbeeb8efe etf: Split timers... |
220 |
} |
25db26a91 net/sched: Introd... |
221 |
|
cbeeb8efe etf: Split timers... |
222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 |
static void timesortedlist_remove(struct Qdisc *sch, struct sk_buff *skb) { struct etf_sched_data *q = qdisc_priv(sch); rb_erase_cached(&skb->rbnode, &q->head); /* The rbnode field in the skb re-uses these fields, now that * we are done with the rbnode, reset them. */ skb->next = NULL; skb->prev = NULL; skb->dev = qdisc_dev(sch); qdisc_qstats_backlog_dec(sch, skb); qdisc_bstats_update(sch, skb); q->last = skb->tstamp; |
25db26a91 net/sched: Introd... |
240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
sch->q.qlen--; } static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; ktime_t now, next; skb = etf_peek_timesortedlist(sch); if (!skb) return NULL; now = q->get_time(); /* Drop if packet has expired while in queue. */ |
25db26a91 net/sched: Introd... |
257 |
if (ktime_before(skb->tstamp, now)) { |
37342bdaf etf: Drop all exp... |
258 |
timesortedlist_drop(sch, skb, now); |
25db26a91 net/sched: Introd... |
259 260 261 262 263 264 265 266 |
skb = NULL; goto out; } /* When in deadline mode, dequeue as soon as possible and change the * txtime from deadline to (now + delta). */ if (q->deadline_mode) { |
cbeeb8efe etf: Split timers... |
267 |
timesortedlist_remove(sch, skb); |
25db26a91 net/sched: Introd... |
268 269 270 271 272 273 274 275 |
skb->tstamp = now; goto out; } next = ktime_sub_ns(skb->tstamp, q->delta); /* Dequeue only if now is within the [txtime - delta, txtime] range. */ if (ktime_after(now, next)) |
cbeeb8efe etf: Split timers... |
276 |
timesortedlist_remove(sch, skb); |
25db26a91 net/sched: Introd... |
277 278 279 280 281 282 283 284 285 |
else skb = NULL; out: /* Now we may need to re-arm the qdisc watchdog for the next packet. */ reset_watchdog(sch); return skb; } |
88cab7716 net/sched: Add HW... |
286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 |
static void etf_disable_offload(struct net_device *dev, struct etf_sched_data *q) { struct tc_etf_qopt_offload etf = { }; const struct net_device_ops *ops; int err; if (!q->offload) return; ops = dev->netdev_ops; if (!ops->ndo_setup_tc) return; etf.queue = q->queue; etf.enable = 0; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); if (err < 0) pr_warn("Couldn't disable ETF offload for queue %d ", etf.queue); } static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_etf_qopt_offload etf = { }; int err; if (q->offload) return 0; if (!ops->ndo_setup_tc) { NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload"); return -EOPNOTSUPP; } etf.queue = q->queue; etf.enable = 1; err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf); if (err < 0) { NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload"); return err; } return 0; } |
25db26a91 net/sched: Introd... |
336 337 338 339 340 341 342 343 344 345 346 347 348 349 |
static int etf_init(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct etf_sched_data *q = qdisc_priv(sch); struct net_device *dev = qdisc_dev(sch); struct nlattr *tb[TCA_ETF_MAX + 1]; struct tc_etf_qopt *qopt; int err; if (!opt) { NL_SET_ERR_MSG(extack, "Missing ETF qdisc options which are mandatory"); return -EINVAL; } |
8cb081746 netlink: make val... |
350 351 |
err = nla_parse_nested_deprecated(tb, TCA_ETF_MAX, opt, etf_policy, extack); |
25db26a91 net/sched: Introd... |
352 353 354 355 356 357 358 359 360 |
if (err < 0) return err; if (!tb[TCA_ETF_PARMS]) { NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters"); return -EINVAL; } qopt = nla_data(tb[TCA_ETF_PARMS]); |
88cab7716 net/sched: Add HW... |
361 362 |
pr_debug("delta %d clockid %d offload %s deadline %s ", |
25db26a91 net/sched: Introd... |
363 |
qopt->delta, qopt->clockid, |
88cab7716 net/sched: Add HW... |
364 |
OFFLOAD_IS_ON(qopt) ? "on" : "off", |
25db26a91 net/sched: Introd... |
365 366 367 368 369 370 371 |
DEADLINE_MODE_IS_ON(qopt) ? "on" : "off"); err = validate_input_params(qopt, extack); if (err < 0) return err; q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0); |
88cab7716 net/sched: Add HW... |
372 373 374 375 376 |
if (OFFLOAD_IS_ON(qopt)) { err = etf_enable_offload(dev, q, extack); if (err < 0) return err; } |
25db26a91 net/sched: Introd... |
377 378 379 |
/* Everything went OK, save the parameters used. */ q->delta = qopt->delta; q->clockid = qopt->clockid; |
88cab7716 net/sched: Add HW... |
380 |
q->offload = OFFLOAD_IS_ON(qopt); |
25db26a91 net/sched: Introd... |
381 |
q->deadline_mode = DEADLINE_MODE_IS_ON(qopt); |
d14d2b206 etf: Add skip_soc... |
382 |
q->skip_sock_check = SKIP_SOCK_CHECK_IS_SET(qopt); |
25db26a91 net/sched: Introd... |
383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 |
switch (q->clockid) { case CLOCK_REALTIME: q->get_time = ktime_get_real; break; case CLOCK_MONOTONIC: q->get_time = ktime_get; break; case CLOCK_BOOTTIME: q->get_time = ktime_get_boottime; break; case CLOCK_TAI: q->get_time = ktime_get_clocktai; break; default: NL_SET_ERR_MSG(extack, "Clockid is not supported"); return -ENOTSUPP; } qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid); return 0; } static void timesortedlist_clear(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); |
09fd4860e etf: Use cached r... |
410 |
struct rb_node *p = rb_first_cached(&q->head); |
25db26a91 net/sched: Introd... |
411 412 413 414 415 |
while (p) { struct sk_buff *skb = rb_to_skb(p); p = rb_next(p); |
09fd4860e etf: Use cached r... |
416 |
rb_erase_cached(&skb->rbnode, &q->head); |
25db26a91 net/sched: Introd... |
417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 |
rtnl_kfree_skbs(skb, skb); sch->q.qlen--; } } static void etf_reset(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); /* Only cancel watchdog if it's been initialized. */ if (q->watchdog.qdisc == sch) qdisc_watchdog_cancel(&q->watchdog); /* No matter which mode we are on, it's safe to clear both lists. */ timesortedlist_clear(sch); __qdisc_reset_queue(&sch->q); sch->qstats.backlog = 0; sch->q.qlen = 0; q->last = 0; } static void etf_destroy(struct Qdisc *sch) { struct etf_sched_data *q = qdisc_priv(sch); |
88cab7716 net/sched: Add HW... |
443 |
struct net_device *dev = qdisc_dev(sch); |
25db26a91 net/sched: Introd... |
444 445 446 447 |
/* Only cancel watchdog if it's been initialized. */ if (q->watchdog.qdisc == sch) qdisc_watchdog_cancel(&q->watchdog); |
88cab7716 net/sched: Add HW... |
448 449 |
etf_disable_offload(dev, q); |
25db26a91 net/sched: Introd... |
450 451 452 453 454 455 456 |
} static int etf_dump(struct Qdisc *sch, struct sk_buff *skb) { struct etf_sched_data *q = qdisc_priv(sch); struct tc_etf_qopt opt = { }; struct nlattr *nest; |
ae0be8de9 netlink: make nla... |
457 |
nest = nla_nest_start_noflag(skb, TCA_OPTIONS); |
25db26a91 net/sched: Introd... |
458 459 460 461 462 |
if (!nest) goto nla_put_failure; opt.delta = q->delta; opt.clockid = q->clockid; |
88cab7716 net/sched: Add HW... |
463 464 |
if (q->offload) opt.flags |= TC_ETF_OFFLOAD_ON; |
25db26a91 net/sched: Introd... |
465 466 |
if (q->deadline_mode) opt.flags |= TC_ETF_DEADLINE_MODE_ON; |
d14d2b206 etf: Add skip_soc... |
467 468 |
if (q->skip_sock_check) opt.flags |= TC_ETF_SKIP_SOCK_CHECK; |
25db26a91 net/sched: Introd... |
469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 |
if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt)) goto nla_put_failure; return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); return -1; } static struct Qdisc_ops etf_qdisc_ops __read_mostly = { .id = "etf", .priv_size = sizeof(struct etf_sched_data), .enqueue = etf_enqueue_timesortedlist, .dequeue = etf_dequeue_timesortedlist, .peek = etf_peek_timesortedlist, .init = etf_init, .reset = etf_reset, .destroy = etf_destroy, .dump = etf_dump, .owner = THIS_MODULE, }; static int __init etf_module_init(void) { return register_qdisc(&etf_qdisc_ops); } static void __exit etf_module_exit(void) { unregister_qdisc(&etf_qdisc_ops); } module_init(etf_module_init) module_exit(etf_module_exit) MODULE_LICENSE("GPL"); |