linux/net/sched/sch_fq_pie.c

562 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/* Flow Queue PIE discipline
*
* Copyright (C) 2019 Mohit P. Tahiliani <tahiliani@nitk.edu.in>
* Copyright (C) 2019 Sachin D. Patil <sdp.sachin@gmail.com>
* Copyright (C) 2019 V. Saicharan <vsaicharan1998@gmail.com>
* Copyright (C) 2019 Mohit Bhasi <mohitbhasi1998@gmail.com>
* Copyright (C) 2019 Leslie Monis <lesliemonis@gmail.com>
* Copyright (C) 2019 Gautam Ramakrishnan <gautamramk@gmail.com>
*/
#include <linux/jhash.h>
#include <linux/sizes.h>
#include <linux/vmalloc.h>
#include <net/pkt_cls.h>
#include <net/pie.h>
/* Flow Queue PIE
*
* Principles:
* - Packets are classified on flows.
* - This is a Stochastic model (as we use a hash, several flows might
* be hashed to the same slot)
* - Each flow has a PIE managed queue.
* - Flows are linked onto two (Round Robin) lists,
* so that new flows have priority on old ones.
* - For a given flow, packets are not reordered.
* - Drops during enqueue only.
* - ECN capability is off by default.
* - ECN threshold (if ECN is enabled) is at 10% by default.
* - Uses timestamps to calculate queue delay by default.
*/
/**
* struct fq_pie_flow - contains data for each flow
* @vars: pie vars associated with the flow
* @deficit: number of remaining byte credits
* @backlog: size of data in the flow
* @qlen: number of packets in the flow
* @flowchain: flowchain for the flow
* @head: first packet in the flow
* @tail: last packet in the flow
*/
struct fq_pie_flow {
struct pie_vars vars;
s32 deficit;
u32 backlog;
u32 qlen;
struct list_head flowchain;
struct sk_buff *head;
struct sk_buff *tail;
};
struct fq_pie_sched_data {
struct tcf_proto __rcu *filter_list; /* optional external classifier */
struct tcf_block *block;
struct fq_pie_flow *flows;
struct Qdisc *sch;
struct list_head old_flows;
struct list_head new_flows;
struct pie_params p_params;
u32 ecn_prob;
u32 flows_cnt;
u32 quantum;
u32 memory_limit;
u32 new_flow_count;
u32 memory_usage;
u32 overmemory;
struct pie_stats stats;
struct timer_list adapt_timer;
};
static unsigned int fq_pie_hash(const struct fq_pie_sched_data *q,
struct sk_buff *skb)
{
return reciprocal_scale(skb_get_hash(skb), q->flows_cnt);
}
static unsigned int fq_pie_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
struct tcf_proto *filter;
struct tcf_result res;
int result;
if (TC_H_MAJ(skb->priority) == sch->handle &&
TC_H_MIN(skb->priority) > 0 &&
TC_H_MIN(skb->priority) <= q->flows_cnt)
return TC_H_MIN(skb->priority);
filter = rcu_dereference_bh(q->filter_list);
if (!filter)
return fq_pie_hash(q, skb) + 1;
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
result = tcf_classify(skb, filter, &res, false);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
fallthrough;
case TC_ACT_SHOT:
return 0;
}
#endif
if (TC_H_MIN(res.classid) <= q->flows_cnt)
return TC_H_MIN(res.classid);
}
return 0;
}
/* add skb to flow queue (tail add) */
static inline void flow_queue_add(struct fq_pie_flow *flow,
struct sk_buff *skb)
{
if (!flow->head)
flow->head = skb;
else
flow->tail->next = skb;
flow->tail = skb;
skb->next = NULL;
}
static int fq_pie_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
struct fq_pie_flow *sel_flow;
treewide: Remove uninitialized_var() usage Using uninitialized_var() is dangerous as it papers over real bugs[1] (or can in the future), and suppresses unrelated compiler warnings (e.g. "unused variable"). If the compiler thinks it is uninitialized, either simply initialize the variable or make compiler changes. In preparation for removing[2] the[3] macro[4], remove all remaining needless uses with the following script: git grep '\buninitialized_var\b' | cut -d: -f1 | sort -u | \ xargs perl -pi -e \ 's/\buninitialized_var\(([^\)]+)\)/\1/g; s:\s*/\* (GCC be quiet|to make compiler happy) \*/$::g;' drivers/video/fbdev/riva/riva_hw.c was manually tweaked to avoid pathological white-space. No outstanding warnings were found building allmodconfig with GCC 9.3.0 for x86_64, i386, arm64, arm, powerpc, powerpc64le, s390x, mips, sparc64, alpha, and m68k. [1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/ [2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/ [3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/ [4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/ Reviewed-by: Leon Romanovsky <leonro@mellanox.com> # drivers/infiniband and mlx4/mlx5 Acked-by: Jason Gunthorpe <jgg@mellanox.com> # IB Acked-by: Kalle Valo <kvalo@codeaurora.org> # wireless drivers Reviewed-by: Chao Yu <yuchao0@huawei.com> # erofs Signed-off-by: Kees Cook <keescook@chromium.org>
2020-06-03 20:09:38 +00:00
int ret;
u8 memory_limited = false;
u8 enqueue = false;
u32 pkt_len;
u32 idx;
/* Classifies packet into corresponding flow */
idx = fq_pie_classify(skb, sch, &ret);
sel_flow = &q->flows[idx];
/* Checks whether adding a new packet would exceed memory limit */
get_pie_cb(skb)->mem_usage = skb->truesize;
memory_limited = q->memory_usage > q->memory_limit + skb->truesize;
/* Checks if the qdisc is full */
if (unlikely(qdisc_qlen(sch) >= sch->limit)) {
q->stats.overlimit++;
goto out;
} else if (unlikely(memory_limited)) {
q->overmemory++;
}
if (!pie_drop_early(sch, &q->p_params, &sel_flow->vars,
sel_flow->backlog, skb->len)) {
enqueue = true;
} else if (q->p_params.ecn &&
sel_flow->vars.prob <= (MAX_PROB / 100) * q->ecn_prob &&
INET_ECN_set_ce(skb)) {
/* If packet is ecn capable, mark it if drop probability
* is lower than the parameter ecn_prob, else drop it.
*/
q->stats.ecn_mark++;
enqueue = true;
}
if (enqueue) {
/* Set enqueue time only when dq_rate_estimator is disabled. */
if (!q->p_params.dq_rate_estimator)
pie_set_enqueue_time(skb);
pkt_len = qdisc_pkt_len(skb);
q->stats.packets_in++;
q->memory_usage += skb->truesize;
sch->qstats.backlog += pkt_len;
sch->q.qlen++;
flow_queue_add(sel_flow, skb);
if (list_empty(&sel_flow->flowchain)) {
list_add_tail(&sel_flow->flowchain, &q->new_flows);
q->new_flow_count++;
sel_flow->deficit = q->quantum;
sel_flow->qlen = 0;
sel_flow->backlog = 0;
}
sel_flow->qlen++;
sel_flow->backlog += pkt_len;
return NET_XMIT_SUCCESS;
}
out:
q->stats.dropped++;
sel_flow->vars.accu_prob = 0;
__qdisc_drop(skb, to_free);
qdisc_qstats_drop(sch);
return NET_XMIT_CN;
}
static const struct nla_policy fq_pie_policy[TCA_FQ_PIE_MAX + 1] = {
[TCA_FQ_PIE_LIMIT] = {.type = NLA_U32},
[TCA_FQ_PIE_FLOWS] = {.type = NLA_U32},
[TCA_FQ_PIE_TARGET] = {.type = NLA_U32},
[TCA_FQ_PIE_TUPDATE] = {.type = NLA_U32},
[TCA_FQ_PIE_ALPHA] = {.type = NLA_U32},
[TCA_FQ_PIE_BETA] = {.type = NLA_U32},
[TCA_FQ_PIE_QUANTUM] = {.type = NLA_U32},
[TCA_FQ_PIE_MEMORY_LIMIT] = {.type = NLA_U32},
[TCA_FQ_PIE_ECN_PROB] = {.type = NLA_U32},
[TCA_FQ_PIE_ECN] = {.type = NLA_U32},
[TCA_FQ_PIE_BYTEMODE] = {.type = NLA_U32},
[TCA_FQ_PIE_DQ_RATE_ESTIMATOR] = {.type = NLA_U32},
};
static inline struct sk_buff *dequeue_head(struct fq_pie_flow *flow)
{
struct sk_buff *skb = flow->head;
flow->head = skb->next;
skb->next = NULL;
return skb;
}
static struct sk_buff *fq_pie_qdisc_dequeue(struct Qdisc *sch)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
struct sk_buff *skb = NULL;
struct fq_pie_flow *flow;
struct list_head *head;
u32 pkt_len;
begin:
head = &q->new_flows;
if (list_empty(head)) {
head = &q->old_flows;
if (list_empty(head))
return NULL;
}
flow = list_first_entry(head, struct fq_pie_flow, flowchain);
/* Flow has exhausted all its credits */
if (flow->deficit <= 0) {
flow->deficit += q->quantum;
list_move_tail(&flow->flowchain, &q->old_flows);
goto begin;
}
if (flow->head) {
skb = dequeue_head(flow);
pkt_len = qdisc_pkt_len(skb);
sch->qstats.backlog -= pkt_len;
sch->q.qlen--;
qdisc_bstats_update(sch, skb);
}
if (!skb) {
/* force a pass through old_flows to prevent starvation */
if (head == &q->new_flows && !list_empty(&q->old_flows))
list_move_tail(&flow->flowchain, &q->old_flows);
else
list_del_init(&flow->flowchain);
goto begin;
}
flow->qlen--;
flow->deficit -= pkt_len;
flow->backlog -= pkt_len;
q->memory_usage -= get_pie_cb(skb)->mem_usage;
pie_process_dequeue(skb, &q->p_params, &flow->vars, flow->backlog);
return skb;
}
static int fq_pie_change(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
struct nlattr *tb[TCA_FQ_PIE_MAX + 1];
unsigned int len_dropped = 0;
unsigned int num_dropped = 0;
int err;
if (!opt)
return -EINVAL;
err = nla_parse_nested(tb, TCA_FQ_PIE_MAX, opt, fq_pie_policy, extack);
if (err < 0)
return err;
sch_tree_lock(sch);
if (tb[TCA_FQ_PIE_LIMIT]) {
u32 limit = nla_get_u32(tb[TCA_FQ_PIE_LIMIT]);
q->p_params.limit = limit;
sch->limit = limit;
}
if (tb[TCA_FQ_PIE_FLOWS]) {
if (q->flows) {
NL_SET_ERR_MSG_MOD(extack,
"Number of flows cannot be changed");
goto flow_error;
}
q->flows_cnt = nla_get_u32(tb[TCA_FQ_PIE_FLOWS]);
net/sched: fix infinite loop in sch_fq_pie this command hangs forever: # tc qdisc add dev eth0 root fq_pie flows 65536 watchdog: BUG: soft lockup - CPU#1 stuck for 23s! [tc:1028] [...] CPU: 1 PID: 1028 Comm: tc Not tainted 5.7.0-rc6+ #167 RIP: 0010:fq_pie_init+0x60e/0x8b7 [sch_fq_pie] Code: 4c 89 65 50 48 89 f8 48 c1 e8 03 42 80 3c 30 00 0f 85 2a 02 00 00 48 8d 7d 10 4c 89 65 58 48 89 f8 48 c1 e8 03 42 80 3c 30 00 <0f> 85 a7 01 00 00 48 8d 7d 18 48 c7 45 10 46 c3 23 00 48 89 f8 48 RSP: 0018:ffff888138d67468 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: 1ffff9200018d2b2 RBX: ffff888139c1c400 RCX: ffffffffffffffff RDX: 000000000000c5e8 RSI: ffffc900000e5000 RDI: ffffc90000c69590 RBP: ffffc90000c69580 R08: fffffbfff79a9699 R09: fffffbfff79a9699 R10: 0000000000000700 R11: fffffbfff79a9698 R12: ffffc90000c695d0 R13: 0000000000000000 R14: dffffc0000000000 R15: 000000002347c5e8 FS: 00007f01e1850e40(0000) GS:ffff88814c880000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000067c340 CR3: 000000013864c000 CR4: 0000000000340ee0 Call Trace: qdisc_create+0x3fd/0xeb0 tc_modify_qdisc+0x3be/0x14a0 rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x121/0x350 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 we can't accept 65536 as a valid number for 'nflows', because the loop on 'idx' in fq_pie_init() will never end. The extack message is correct, but it doesn't say that 0 is not a valid number for 'flows': while at it, fix this also. Add a tdc selftest to check correct validation of 'flows'. CC: Ivan Vecera <ivecera@redhat.com> Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Ivan Vecera <ivecera@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-27 00:04:26 +00:00
if (!q->flows_cnt || q->flows_cnt >= 65536) {
NL_SET_ERR_MSG_MOD(extack,
net/sched: fix infinite loop in sch_fq_pie this command hangs forever: # tc qdisc add dev eth0 root fq_pie flows 65536 watchdog: BUG: soft lockup - CPU#1 stuck for 23s! [tc:1028] [...] CPU: 1 PID: 1028 Comm: tc Not tainted 5.7.0-rc6+ #167 RIP: 0010:fq_pie_init+0x60e/0x8b7 [sch_fq_pie] Code: 4c 89 65 50 48 89 f8 48 c1 e8 03 42 80 3c 30 00 0f 85 2a 02 00 00 48 8d 7d 10 4c 89 65 58 48 89 f8 48 c1 e8 03 42 80 3c 30 00 <0f> 85 a7 01 00 00 48 8d 7d 18 48 c7 45 10 46 c3 23 00 48 89 f8 48 RSP: 0018:ffff888138d67468 EFLAGS: 00000246 ORIG_RAX: ffffffffffffff13 RAX: 1ffff9200018d2b2 RBX: ffff888139c1c400 RCX: ffffffffffffffff RDX: 000000000000c5e8 RSI: ffffc900000e5000 RDI: ffffc90000c69590 RBP: ffffc90000c69580 R08: fffffbfff79a9699 R09: fffffbfff79a9699 R10: 0000000000000700 R11: fffffbfff79a9698 R12: ffffc90000c695d0 R13: 0000000000000000 R14: dffffc0000000000 R15: 000000002347c5e8 FS: 00007f01e1850e40(0000) GS:ffff88814c880000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 000000000067c340 CR3: 000000013864c000 CR4: 0000000000340ee0 Call Trace: qdisc_create+0x3fd/0xeb0 tc_modify_qdisc+0x3be/0x14a0 rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x121/0x350 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 we can't accept 65536 as a valid number for 'nflows', because the loop on 'idx' in fq_pie_init() will never end. The extack message is correct, but it doesn't say that 0 is not a valid number for 'flows': while at it, fix this also. Add a tdc selftest to check correct validation of 'flows'. CC: Ivan Vecera <ivecera@redhat.com> Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Ivan Vecera <ivecera@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-27 00:04:26 +00:00
"Number of flows must range in [1..65535]");
goto flow_error;
}
}
/* convert from microseconds to pschedtime */
if (tb[TCA_FQ_PIE_TARGET]) {
/* target is in us */
u32 target = nla_get_u32(tb[TCA_FQ_PIE_TARGET]);
/* convert to pschedtime */
q->p_params.target =
PSCHED_NS2TICKS((u64)target * NSEC_PER_USEC);
}
/* tupdate is in jiffies */
if (tb[TCA_FQ_PIE_TUPDATE])
q->p_params.tupdate =
usecs_to_jiffies(nla_get_u32(tb[TCA_FQ_PIE_TUPDATE]));
if (tb[TCA_FQ_PIE_ALPHA])
q->p_params.alpha = nla_get_u32(tb[TCA_FQ_PIE_ALPHA]);
if (tb[TCA_FQ_PIE_BETA])
q->p_params.beta = nla_get_u32(tb[TCA_FQ_PIE_BETA]);
if (tb[TCA_FQ_PIE_QUANTUM])
q->quantum = nla_get_u32(tb[TCA_FQ_PIE_QUANTUM]);
if (tb[TCA_FQ_PIE_MEMORY_LIMIT])
q->memory_limit = nla_get_u32(tb[TCA_FQ_PIE_MEMORY_LIMIT]);
if (tb[TCA_FQ_PIE_ECN_PROB])
q->ecn_prob = nla_get_u32(tb[TCA_FQ_PIE_ECN_PROB]);
if (tb[TCA_FQ_PIE_ECN])
q->p_params.ecn = nla_get_u32(tb[TCA_FQ_PIE_ECN]);
if (tb[TCA_FQ_PIE_BYTEMODE])
q->p_params.bytemode = nla_get_u32(tb[TCA_FQ_PIE_BYTEMODE]);
if (tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR])
q->p_params.dq_rate_estimator =
nla_get_u32(tb[TCA_FQ_PIE_DQ_RATE_ESTIMATOR]);
/* Drop excess packets if new limit is lower */
while (sch->q.qlen > sch->limit) {
struct sk_buff *skb = fq_pie_qdisc_dequeue(sch);
len_dropped += qdisc_pkt_len(skb);
num_dropped += 1;
rtnl_kfree_skbs(skb, skb);
}
qdisc_tree_reduce_backlog(sch, num_dropped, len_dropped);
sch_tree_unlock(sch);
return 0;
flow_error:
sch_tree_unlock(sch);
return -EINVAL;
}
static void fq_pie_timer(struct timer_list *t)
{
struct fq_pie_sched_data *q = from_timer(q, t, adapt_timer);
struct Qdisc *sch = q->sch;
spinlock_t *root_lock; /* to lock qdisc for probability calculations */
u16 idx;
root_lock = qdisc_lock(qdisc_root_sleeping(sch));
spin_lock(root_lock);
for (idx = 0; idx < q->flows_cnt; idx++)
pie_calculate_probability(&q->p_params, &q->flows[idx].vars,
q->flows[idx].backlog);
/* reset the timer to fire after 'tupdate' jiffies. */
if (q->p_params.tupdate)
mod_timer(&q->adapt_timer, jiffies + q->p_params.tupdate);
spin_unlock(root_lock);
}
static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
int err;
u16 idx;
pie_params_init(&q->p_params);
sch->limit = 10 * 1024;
q->p_params.limit = sch->limit;
q->quantum = psched_mtu(qdisc_dev(sch));
q->sch = sch;
q->ecn_prob = 10;
q->flows_cnt = 1024;
q->memory_limit = SZ_32M;
INIT_LIST_HEAD(&q->new_flows);
INIT_LIST_HEAD(&q->old_flows);
net/sched: fq_pie: initialize timer earlier in fq_pie_init() with the following tdc testcase: 83be: (qdisc, fq_pie) Create FQ-PIE with invalid number of flows as fq_pie_init() fails, fq_pie_destroy() is called to clean up. Since the timer is not yet initialized, it's possible to observe a splat like this: INFO: trying to register non-static key. the code is fine but needs lockdep annotation. turning off the locking correctness validator. CPU: 0 PID: 975 Comm: tc Not tainted 5.10.0-rc4+ #298 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x99/0xcb register_lock_class+0x12dd/0x1750 __lock_acquire+0xfe/0x3970 lock_acquire+0x1c8/0x7f0 del_timer_sync+0x49/0xd0 fq_pie_destroy+0x3f/0x80 [sch_fq_pie] qdisc_create+0x916/0x1160 tc_modify_qdisc+0x3c4/0x1630 rtnetlink_rcv_msg+0x346/0x8e0 netlink_unicast+0x439/0x630 netlink_sendmsg+0x719/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5ba/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] ODEBUG: assert_init not available (active state 0) object type: timer_list hint: 0x0 WARNING: CPU: 0 PID: 975 at lib/debugobjects.c:508 debug_print_object+0x162/0x210 [...] Call Trace: debug_object_assert_init+0x268/0x380 try_to_del_timer_sync+0x6a/0x100 del_timer_sync+0x9e/0xd0 fq_pie_destroy+0x3f/0x80 [sch_fq_pie] qdisc_create+0x916/0x1160 tc_modify_qdisc+0x3c4/0x1630 rtnetlink_rcv_msg+0x346/0x8e0 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x719/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5ba/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xa9 fix it moving timer_setup() before any failure, like it was done on 'red' with former commit 608b4adab178 ("net_sched: initialize timer earlier in red_init()"). Fixes: ec97ecf1ebe4 ("net: sched: add Flow Queue PIE packet scheduler") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Cong Wang <cong.wang@bytedance.com> Link: https://lore.kernel.org/r/2e78e01c504c633ebdff18d041833cf2e079a3a4.1607020450.git.dcaratti@redhat.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2020-12-03 18:40:47 +00:00
timer_setup(&q->adapt_timer, fq_pie_timer, 0);
if (opt) {
err = fq_pie_change(sch, opt, extack);
if (err)
return err;
}
err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
if (err)
goto init_failure;
q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_pie_flow),
GFP_KERNEL);
if (!q->flows) {
err = -ENOMEM;
goto init_failure;
}
for (idx = 0; idx < q->flows_cnt; idx++) {
struct fq_pie_flow *flow = q->flows + idx;
INIT_LIST_HEAD(&flow->flowchain);
pie_vars_init(&flow->vars);
}
mod_timer(&q->adapt_timer, jiffies + HZ / 2);
return 0;
init_failure:
q->flows_cnt = 0;
return err;
}
static int fq_pie_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
struct nlattr *opts;
opts = nla_nest_start(skb, TCA_OPTIONS);
if (!opts)
return -EMSGSIZE;
/* convert target from pschedtime to us */
if (nla_put_u32(skb, TCA_FQ_PIE_LIMIT, sch->limit) ||
nla_put_u32(skb, TCA_FQ_PIE_FLOWS, q->flows_cnt) ||
nla_put_u32(skb, TCA_FQ_PIE_TARGET,
((u32)PSCHED_TICKS2NS(q->p_params.target)) /
NSEC_PER_USEC) ||
nla_put_u32(skb, TCA_FQ_PIE_TUPDATE,
jiffies_to_usecs(q->p_params.tupdate)) ||
nla_put_u32(skb, TCA_FQ_PIE_ALPHA, q->p_params.alpha) ||
nla_put_u32(skb, TCA_FQ_PIE_BETA, q->p_params.beta) ||
nla_put_u32(skb, TCA_FQ_PIE_QUANTUM, q->quantum) ||
nla_put_u32(skb, TCA_FQ_PIE_MEMORY_LIMIT, q->memory_limit) ||
nla_put_u32(skb, TCA_FQ_PIE_ECN_PROB, q->ecn_prob) ||
nla_put_u32(skb, TCA_FQ_PIE_ECN, q->p_params.ecn) ||
nla_put_u32(skb, TCA_FQ_PIE_BYTEMODE, q->p_params.bytemode) ||
nla_put_u32(skb, TCA_FQ_PIE_DQ_RATE_ESTIMATOR,
q->p_params.dq_rate_estimator))
goto nla_put_failure;
return nla_nest_end(skb, opts);
nla_put_failure:
nla_nest_cancel(skb, opts);
return -EMSGSIZE;
}
static int fq_pie_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
struct tc_fq_pie_xstats st = {
.packets_in = q->stats.packets_in,
.overlimit = q->stats.overlimit,
.overmemory = q->overmemory,
.dropped = q->stats.dropped,
.ecn_mark = q->stats.ecn_mark,
.new_flow_count = q->new_flow_count,
.memory_usage = q->memory_usage,
};
struct list_head *pos;
sch_tree_lock(sch);
list_for_each(pos, &q->new_flows)
st.new_flows_len++;
list_for_each(pos, &q->old_flows)
st.old_flows_len++;
sch_tree_unlock(sch);
return gnet_stats_copy_app(d, &st, sizeof(st));
}
static void fq_pie_reset(struct Qdisc *sch)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
u16 idx;
INIT_LIST_HEAD(&q->new_flows);
INIT_LIST_HEAD(&q->old_flows);
for (idx = 0; idx < q->flows_cnt; idx++) {
struct fq_pie_flow *flow = q->flows + idx;
/* Removes all packets from flow */
rtnl_kfree_skbs(flow->head, flow->tail);
flow->head = NULL;
INIT_LIST_HEAD(&flow->flowchain);
pie_vars_init(&flow->vars);
}
sch->q.qlen = 0;
sch->qstats.backlog = 0;
}
static void fq_pie_destroy(struct Qdisc *sch)
{
struct fq_pie_sched_data *q = qdisc_priv(sch);
tcf_block_put(q->block);
del_timer_sync(&q->adapt_timer);
kvfree(q->flows);
}
static struct Qdisc_ops fq_pie_qdisc_ops __read_mostly = {
.id = "fq_pie",
.priv_size = sizeof(struct fq_pie_sched_data),
.enqueue = fq_pie_qdisc_enqueue,
.dequeue = fq_pie_qdisc_dequeue,
.peek = qdisc_peek_dequeued,
.init = fq_pie_init,
.destroy = fq_pie_destroy,
.reset = fq_pie_reset,
.change = fq_pie_change,
.dump = fq_pie_dump,
.dump_stats = fq_pie_dump_stats,
.owner = THIS_MODULE,
};
static int __init fq_pie_module_init(void)
{
return register_qdisc(&fq_pie_qdisc_ops);
}
static void __exit fq_pie_module_exit(void)
{
unregister_qdisc(&fq_pie_qdisc_ops);
}
module_init(fq_pie_module_init);
module_exit(fq_pie_module_exit);
MODULE_DESCRIPTION("Flow Queue Proportional Integral controller Enhanced (FQ-PIE)");
MODULE_AUTHOR("Mohit P. Tahiliani");
MODULE_LICENSE("GPL");