linux/net/sched/sch_drr.c

500 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* net/sched/sch_drr.c Deficit Round Robin scheduler
*
* Copyright (c) 2008 Patrick McHardy <kaber@trash.net>
*/
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/pkt_sched.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
struct drr_class {
struct Qdisc_class_common common;
struct gnet_stats_basic_sync bstats;
struct gnet_stats_queue qstats;
struct net_rate_estimator __rcu *rate_est;
struct list_head alist;
struct Qdisc *qdisc;
u32 quantum;
u32 deficit;
};
struct drr_sched {
struct list_head active;
struct tcf_proto __rcu *filter_list;
struct tcf_block *block;
struct Qdisc_class_hash clhash;
};
static struct drr_class *drr_find_class(struct Qdisc *sch, u32 classid)
{
struct drr_sched *q = qdisc_priv(sch);
struct Qdisc_class_common *clc;
clc = qdisc_class_find(&q->clhash, classid);
if (clc == NULL)
return NULL;
return container_of(clc, struct drr_class, common);
}
static const struct nla_policy drr_policy[TCA_DRR_MAX + 1] = {
[TCA_DRR_QUANTUM] = { .type = NLA_U32 },
};
static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
struct nlattr **tca, unsigned long *arg,
struct netlink_ext_ack *extack)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl = (struct drr_class *)*arg;
struct nlattr *opt = tca[TCA_OPTIONS];
struct nlattr *tb[TCA_DRR_MAX + 1];
u32 quantum;
int err;
if (!opt) {
NL_SET_ERR_MSG(extack, "DRR options are required for this operation");
return -EINVAL;
}
netlink: make validation more configurable for future strictness We currently have two levels of strict validation: 1) liberal (default) - undefined (type >= max) & NLA_UNSPEC attributes accepted - attribute length >= expected accepted - garbage at end of message accepted 2) strict (opt-in) - NLA_UNSPEC attributes accepted - attribute length >= expected accepted Split out parsing strictness into four different options: * TRAILING - check that there's no trailing data after parsing attributes (in message or nested) * MAXTYPE - reject attrs > max known type * UNSPEC - reject attributes with NLA_UNSPEC policy entries * STRICT_ATTRS - strictly validate attribute size The default for future things should be *everything*. The current *_strict() is a combination of TRAILING and MAXTYPE, and is renamed to _deprecated_strict(). The current regular parsing has none of this, and is renamed to *_parse_deprecated(). Additionally it allows us to selectively set one of the new flags even on old policies. Notably, the UNSPEC flag could be useful in this case, since it can be arranged (by filling in the policy) to not be an incompatible userspace ABI change, but would then going forward prevent forgetting attribute entries. Similar can apply to the POLICY flag. We end up with the following renames: * nla_parse -> nla_parse_deprecated * nla_parse_strict -> nla_parse_deprecated_strict * nlmsg_parse -> nlmsg_parse_deprecated * nlmsg_parse_strict -> nlmsg_parse_deprecated_strict * nla_parse_nested -> nla_parse_nested_deprecated * nla_validate_nested -> nla_validate_nested_deprecated Using spatch, of course: @@ expression TB, MAX, HEAD, LEN, POL, EXT; @@ -nla_parse(TB, MAX, HEAD, LEN, POL, EXT) +nla_parse_deprecated(TB, MAX, HEAD, LEN, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression NLH, HDRLEN, TB, MAX, POL, EXT; @@ -nlmsg_parse_strict(NLH, HDRLEN, TB, MAX, POL, EXT) +nlmsg_parse_deprecated_strict(NLH, HDRLEN, TB, MAX, POL, EXT) @@ expression TB, MAX, NLA, POL, EXT; @@ -nla_parse_nested(TB, MAX, NLA, POL, EXT) +nla_parse_nested_deprecated(TB, MAX, NLA, POL, EXT) @@ expression START, MAX, POL, EXT; @@ -nla_validate_nested(START, MAX, POL, EXT) +nla_validate_nested_deprecated(START, MAX, POL, EXT) @@ expression NLH, HDRLEN, MAX, POL, EXT; @@ -nlmsg_validate(NLH, HDRLEN, MAX, POL, EXT) +nlmsg_validate_deprecated(NLH, HDRLEN, MAX, POL, EXT) For this patch, don't actually add the strict, non-renamed versions yet so that it breaks compile if I get it wrong. Also, while at it, make nla_validate and nla_parse go down to a common __nla_validate_parse() function to avoid code duplication. Ultimately, this allows us to have very strict validation for every new caller of nla_parse()/nlmsg_parse() etc as re-introduced in the next patch, while existing things will continue to work as is. In effect then, this adds fully strict validation for any new command. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-26 12:07:28 +00:00
err = nla_parse_nested_deprecated(tb, TCA_DRR_MAX, opt, drr_policy,
extack);
if (err < 0)
return err;
if (tb[TCA_DRR_QUANTUM]) {
quantum = nla_get_u32(tb[TCA_DRR_QUANTUM]);
if (quantum == 0) {
NL_SET_ERR_MSG(extack, "Specified DRR quantum cannot be zero");
return -EINVAL;
}
} else
quantum = psched_mtu(qdisc_dev(sch));
if (cl != NULL) {
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, NULL,
&cl->rate_est,
net: sched: Remove Qdisc::running sequence counter The Qdisc::running sequence counter has two uses: 1. Reliably reading qdisc's tc statistics while the qdisc is running (a seqcount read/retry loop at gnet_stats_add_basic()). 2. As a flag, indicating whether the qdisc in question is running (without any retry loops). For the first usage, the Qdisc::running sequence counter write section, qdisc_run_begin() => qdisc_run_end(), covers a much wider area than what is actually needed: the raw qdisc's bstats update. A u64_stats sync point was thus introduced (in previous commits) inside the bstats structure itself. A local u64_stats write section is then started and stopped for the bstats updates. Use that u64_stats sync point mechanism for the bstats read/retry loop at gnet_stats_add_basic(). For the second qdisc->running usage, a __QDISC_STATE_RUNNING bit flag, accessed with atomic bitops, is sufficient. Using a bit flag instead of a sequence counter at qdisc_run_begin/end() and qdisc_is_running() leads to the SMP barriers implicitly added through raw_read_seqcount() and write_seqcount_begin/end() getting removed. All call sites have been surveyed though, and no required ordering was identified. Now that the qdisc->running sequence counter is no longer used, remove it. Note, using u64_stats implies no sequence counter protection for 64-bit architectures. This can lead to the qdisc tc statistics "packets" vs. "bytes" values getting out of sync on rare occasions. The individual values will still be valid. Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16 08:49:10 +00:00
NULL, true,
tca[TCA_RATE]);
if (err) {
NL_SET_ERR_MSG(extack, "Failed to replace estimator");
return err;
}
}
sch_tree_lock(sch);
if (tb[TCA_DRR_QUANTUM])
cl->quantum = quantum;
sch_tree_unlock(sch);
return 0;
}
cl = kzalloc(sizeof(struct drr_class), GFP_KERNEL);
if (cl == NULL)
return -ENOBUFS;
gnet_stats_basic_sync_init(&cl->bstats);
cl->common.classid = classid;
cl->quantum = quantum;
cl->qdisc = qdisc_create_dflt(sch->dev_queue,
&pfifo_qdisc_ops, classid,
NULL);
if (cl->qdisc == NULL)
cl->qdisc = &noop_qdisc;
else
qdisc_hash_add(cl->qdisc, true);
if (tca[TCA_RATE]) {
err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
net: sched: Remove Qdisc::running sequence counter The Qdisc::running sequence counter has two uses: 1. Reliably reading qdisc's tc statistics while the qdisc is running (a seqcount read/retry loop at gnet_stats_add_basic()). 2. As a flag, indicating whether the qdisc in question is running (without any retry loops). For the first usage, the Qdisc::running sequence counter write section, qdisc_run_begin() => qdisc_run_end(), covers a much wider area than what is actually needed: the raw qdisc's bstats update. A u64_stats sync point was thus introduced (in previous commits) inside the bstats structure itself. A local u64_stats write section is then started and stopped for the bstats updates. Use that u64_stats sync point mechanism for the bstats read/retry loop at gnet_stats_add_basic(). For the second qdisc->running usage, a __QDISC_STATE_RUNNING bit flag, accessed with atomic bitops, is sufficient. Using a bit flag instead of a sequence counter at qdisc_run_begin/end() and qdisc_is_running() leads to the SMP barriers implicitly added through raw_read_seqcount() and write_seqcount_begin/end() getting removed. All call sites have been surveyed though, and no required ordering was identified. Now that the qdisc->running sequence counter is no longer used, remove it. Note, using u64_stats implies no sequence counter protection for 64-bit architectures. This can lead to the qdisc tc statistics "packets" vs. "bytes" values getting out of sync on rare occasions. The individual values will still be valid. Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16 08:49:10 +00:00
NULL, true, tca[TCA_RATE]);
if (err) {
NL_SET_ERR_MSG(extack, "Failed to replace estimator");
qdisc_put(cl->qdisc);
kfree(cl);
return err;
}
}
sch_tree_lock(sch);
qdisc_class_hash_insert(&q->clhash, &cl->common);
sch_tree_unlock(sch);
qdisc_class_hash_grow(sch, &q->clhash);
*arg = (unsigned long)cl;
return 0;
}
static void drr_destroy_class(struct Qdisc *sch, struct drr_class *cl)
{
gen_kill_estimator(&cl->rate_est);
qdisc_put(cl->qdisc);
kfree(cl);
}
static int drr_delete_class(struct Qdisc *sch, unsigned long arg,
struct netlink_ext_ack *extack)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl = (struct drr_class *)arg;
if (qdisc_class_in_use(&cl->common)) {
NL_SET_ERR_MSG(extack, "DRR class is in use");
return -EBUSY;
}
sch_tree_lock(sch);
qdisc_purge_queue(cl->qdisc);
qdisc_class_hash_remove(&q->clhash, &cl->common);
sch_tree_unlock(sch);
drr_destroy_class(sch, cl);
return 0;
}
static unsigned long drr_search_class(struct Qdisc *sch, u32 classid)
{
return (unsigned long)drr_find_class(sch, classid);
}
static struct tcf_block *drr_tcf_block(struct Qdisc *sch, unsigned long cl,
struct netlink_ext_ack *extack)
{
struct drr_sched *q = qdisc_priv(sch);
if (cl) {
NL_SET_ERR_MSG(extack, "DRR classid must be zero");
return NULL;
}
return q->block;
}
static unsigned long drr_bind_tcf(struct Qdisc *sch, unsigned long parent,
u32 classid)
{
struct drr_class *cl = drr_find_class(sch, classid);
if (cl)
qdisc_class_get(&cl->common);
return (unsigned long)cl;
}
static void drr_unbind_tcf(struct Qdisc *sch, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
qdisc_class_put(&cl->common);
}
static int drr_graft_class(struct Qdisc *sch, unsigned long arg,
struct Qdisc *new, struct Qdisc **old,
struct netlink_ext_ack *extack)
{
struct drr_class *cl = (struct drr_class *)arg;
if (new == NULL) {
new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
cl->common.classid, NULL);
if (new == NULL)
new = &noop_qdisc;
}
*old = qdisc_replace(sch, new, &cl->qdisc);
return 0;
}
static struct Qdisc *drr_class_leaf(struct Qdisc *sch, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
return cl->qdisc;
}
static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg)
{
struct drr_class *cl = (struct drr_class *)arg;
list_del(&cl->alist);
}
static int drr_dump_class(struct Qdisc *sch, unsigned long arg,
struct sk_buff *skb, struct tcmsg *tcm)
{
struct drr_class *cl = (struct drr_class *)arg;
struct nlattr *nest;
tcm->tcm_parent = TC_H_ROOT;
tcm->tcm_handle = cl->common.classid;
tcm->tcm_info = cl->qdisc->handle;
nest = nla_nest_start_noflag(skb, TCA_OPTIONS);
if (nest == NULL)
goto nla_put_failure;
if (nla_put_u32(skb, TCA_DRR_QUANTUM, cl->quantum))
goto nla_put_failure;
return nla_nest_end(skb, nest);
nla_put_failure:
nla_nest_cancel(skb, nest);
return -EMSGSIZE;
}
static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
struct gnet_dump *d)
{
struct drr_class *cl = (struct drr_class *)arg;
__u32 qlen = qdisc_qlen_sum(cl->qdisc);
struct Qdisc *cl_q = cl->qdisc;
struct tc_drr_stats xstats;
memset(&xstats, 0, sizeof(xstats));
if (qlen)
xstats.deficit = cl->deficit;
net: sched: Remove Qdisc::running sequence counter The Qdisc::running sequence counter has two uses: 1. Reliably reading qdisc's tc statistics while the qdisc is running (a seqcount read/retry loop at gnet_stats_add_basic()). 2. As a flag, indicating whether the qdisc in question is running (without any retry loops). For the first usage, the Qdisc::running sequence counter write section, qdisc_run_begin() => qdisc_run_end(), covers a much wider area than what is actually needed: the raw qdisc's bstats update. A u64_stats sync point was thus introduced (in previous commits) inside the bstats structure itself. A local u64_stats write section is then started and stopped for the bstats updates. Use that u64_stats sync point mechanism for the bstats read/retry loop at gnet_stats_add_basic(). For the second qdisc->running usage, a __QDISC_STATE_RUNNING bit flag, accessed with atomic bitops, is sufficient. Using a bit flag instead of a sequence counter at qdisc_run_begin/end() and qdisc_is_running() leads to the SMP barriers implicitly added through raw_read_seqcount() and write_seqcount_begin/end() getting removed. All call sites have been surveyed though, and no required ordering was identified. Now that the qdisc->running sequence counter is no longer used, remove it. Note, using u64_stats implies no sequence counter protection for 64-bit architectures. This can lead to the qdisc tc statistics "packets" vs. "bytes" values getting out of sync on rare occasions. The individual values will still be valid. Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-10-16 08:49:10 +00:00
if (gnet_stats_copy_basic(d, NULL, &cl->bstats, true) < 0 ||
gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 ||
gnet_stats_copy_queue(d, cl_q->cpu_qstats, &cl_q->qstats, qlen) < 0)
return -1;
return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
}
static void drr_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
unsigned int i;
if (arg->stop)
return;
for (i = 0; i < q->clhash.hashsize; i++) {
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
if (!tc_qdisc_stats_dump(sch, (unsigned long)cl, arg))
return;
}
}
}
static struct drr_class *drr_classify(struct sk_buff *skb, struct Qdisc *sch,
int *qerr)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct tcf_result res;
struct tcf_proto *fl;
int result;
if (TC_H_MAJ(skb->priority ^ sch->handle) == 0) {
cl = drr_find_class(sch, skb->priority);
if (cl != NULL)
return cl;
}
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
fl = rcu_dereference_bh(q->filter_list);
result = tcf_classify(skb, NULL, fl, &res, false);
if (result >= 0) {
#ifdef CONFIG_NET_CLS_ACT
switch (result) {
case TC_ACT_QUEUED:
case TC_ACT_STOLEN:
case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
fallthrough;
case TC_ACT_SHOT:
return NULL;
}
#endif
cl = (struct drr_class *)res.class;
if (cl == NULL)
cl = drr_find_class(sch, res.classid);
return cl;
}
return NULL;
}
static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
unsigned int len = qdisc_pkt_len(skb);
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
int err = 0;
bool first;
cl = drr_classify(skb, sch, &err);
if (cl == NULL) {
if (err & __NET_XMIT_BYPASS)
qdisc_qstats_drop(sch);
__qdisc_drop(skb, to_free);
return err;
}
first = !cl->qdisc->q.qlen;
err = qdisc_enqueue(skb, cl->qdisc, to_free);
if (unlikely(err != NET_XMIT_SUCCESS)) {
if (net_xmit_drop_count(err)) {
cl->qstats.drops++;
qdisc_qstats_drop(sch);
}
return err;
}
if (first) {
list_add_tail(&cl->alist, &q->active);
cl->deficit = cl->quantum;
}
sch->qstats.backlog += len;
sch->q.qlen++;
return err;
}
static struct sk_buff *drr_dequeue(struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
struct sk_buff *skb;
unsigned int len;
if (list_empty(&q->active))
goto out;
while (1) {
cl = list_first_entry(&q->active, struct drr_class, alist);
skb = cl->qdisc->ops->peek(cl->qdisc);
if (skb == NULL) {
qdisc_warn_nonwc(__func__, cl->qdisc);
goto out;
}
len = qdisc_pkt_len(skb);
if (len <= cl->deficit) {
cl->deficit -= len;
skb = qdisc_dequeue_peeked(cl->qdisc);
if (unlikely(skb == NULL))
goto out;
if (cl->qdisc->q.qlen == 0)
list_del(&cl->alist);
bstats_update(&cl->bstats, skb);
qdisc_bstats_update(sch, skb);
qdisc_qstats_backlog_dec(sch, skb);
sch->q.qlen--;
return skb;
}
cl->deficit += cl->quantum;
list_move_tail(&cl->alist, &q->active);
}
out:
return NULL;
}
static int drr_init_qdisc(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct drr_sched *q = qdisc_priv(sch);
int err;
err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
if (err)
return err;
err = qdisc_class_hash_init(&q->clhash);
if (err < 0)
return err;
INIT_LIST_HEAD(&q->active);
return 0;
}
static void drr_reset_qdisc(struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
unsigned int i;
for (i = 0; i < q->clhash.hashsize; i++) {
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
if (cl->qdisc->q.qlen)
list_del(&cl->alist);
qdisc_reset(cl->qdisc);
}
}
}
static void drr_destroy_qdisc(struct Qdisc *sch)
{
struct drr_sched *q = qdisc_priv(sch);
struct drr_class *cl;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
struct hlist_node *next;
unsigned int i;
tcf_block_put(q->block);
for (i = 0; i < q->clhash.hashsize; i++) {
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry_safe(cl, next, &q->clhash.hash[i],
common.hnode)
drr_destroy_class(sch, cl);
}
qdisc_class_hash_destroy(&q->clhash);
}
static const struct Qdisc_class_ops drr_class_ops = {
.change = drr_change_class,
.delete = drr_delete_class,
.find = drr_search_class,
.tcf_block = drr_tcf_block,
.bind_tcf = drr_bind_tcf,
.unbind_tcf = drr_unbind_tcf,
.graft = drr_graft_class,
.leaf = drr_class_leaf,
.qlen_notify = drr_qlen_notify,
.dump = drr_dump_class,
.dump_stats = drr_dump_class_stats,
.walk = drr_walk,
};
static struct Qdisc_ops drr_qdisc_ops __read_mostly = {
.cl_ops = &drr_class_ops,
.id = "drr",
.priv_size = sizeof(struct drr_sched),
.enqueue = drr_enqueue,
.dequeue = drr_dequeue,
.peek = qdisc_peek_dequeued,
.init = drr_init_qdisc,
.reset = drr_reset_qdisc,
.destroy = drr_destroy_qdisc,
.owner = THIS_MODULE,
};
net/sched: Add module aliases for cls_,sch_,act_ modules No functional change intended, aliases will be used in followup commits. Note for backporters: you may need to add aliases also for modules that are already removed in mainline kernel but still in your version. Patches were generated with the help of Coccinelle scripts like: cat >scripts/coccinelle/misc/tcf_alias.cocci <<EOD virtual patch virtual report @ haskernel @ @@ @ tcf_has_kind depends on report && haskernel @ identifier ops; constant K; @@ static struct tcf_proto_ops ops = { .kind = K, ... }; +char module_alias = K; EOD /usr/bin/spatch -D report --cocci-file scripts/coccinelle/misc/tcf_alias.cocci \ --dir . \ -I ./arch/x86/include -I ./arch/x86/include/generated -I ./include \ -I ./arch/x86/include/uapi -I ./arch/x86/include/generated/uapi \ -I ./include/uapi -I ./include/generated/uapi \ --include ./include/linux/compiler-version.h --include ./include/linux/kconfig.h \ --jobs 8 --chunksize 1 2>/dev/null | \ sed 's/char module_alias = "\([^"]*\)";/MODULE_ALIAS_NET_CLS("\1");/' And analogously for: static struct tc_action_ops ops = { .kind = K, static struct Qdisc_ops ops = { .id = K, (Someone familiar would be able to fit those into one .cocci file without sed post processing.) Signed-off-by: Michal Koutný <mkoutny@suse.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Reviewed-by: Jiri Pirko <jiri@nvidia.com> Link: https://lore.kernel.org/r/20240201130943.19536-3-mkoutny@suse.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-02-01 13:09:41 +00:00
MODULE_ALIAS_NET_SCH("drr");
static int __init drr_init(void)
{
return register_qdisc(&drr_qdisc_ops);
}
static void __exit drr_exit(void)
{
unregister_qdisc(&drr_qdisc_ops);
}
module_init(drr_init);
module_exit(drr_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("Deficit Round Robin scheduler");