linux_dsm_epyc7002/net/sched/sch_mq.c

247 lines
5.8 KiB
C
Raw Normal View History

/*
* net/sched/sch_mq.c Classful multiqueue dummy scheduler
*
* Copyright (c) 2009 Patrick McHardy <kaber@trash.net>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* version 2 as published by the Free Software Foundation.
*/
#include <linux/types.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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
struct mq_sched {
struct Qdisc **qdiscs;
};
static void mq_destroy(struct Qdisc *sch)
{
struct net_device *dev = qdisc_dev(sch);
struct mq_sched *priv = qdisc_priv(sch);
unsigned int ntx;
if (!priv->qdiscs)
return;
for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
qdisc_destroy(priv->qdiscs[ntx]);
kfree(priv->qdiscs);
}
static int mq_init(struct Qdisc *sch, struct nlattr *opt)
{
struct net_device *dev = qdisc_dev(sch);
struct mq_sched *priv = qdisc_priv(sch);
struct netdev_queue *dev_queue;
struct Qdisc *qdisc;
unsigned int ntx;
if (sch->parent != TC_H_ROOT)
return -EOPNOTSUPP;
if (!netif_is_multiqueue(dev))
return -EOPNOTSUPP;
/* pre-allocate qdiscs, attachment can't fail */
priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
GFP_KERNEL);
if (priv->qdiscs == NULL)
return -ENOMEM;
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
dev_queue = netdev_get_tx_queue(dev, ntx);
qdisc = qdisc_create_dflt(dev_queue, get_default_qdisc_ops(dev, ntx),
TC_H_MAKE(TC_H_MAJ(sch->handle),
TC_H_MIN(ntx + 1)));
if (qdisc == NULL)
goto err;
priv->qdiscs[ntx] = qdisc;
net_sched: fix qdisc_tree_decrease_qlen() races qdisc_tree_decrease_qlen() suffers from two problems on multiqueue devices. One problem is that it updates sch->q.qlen and sch->qstats.drops on the mq/mqprio root qdisc, while it should not : Daniele reported underflows errors : [ 681.774821] PAX: sch->q.qlen: 0 n: 1 [ 681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head; [ 681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G O 4.2.6.201511282239-1-grsec #1 [ 681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015 [ 681.774956] ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c [ 681.774959] ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b [ 681.774960] ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001 [ 681.774962] Call Trace: [ 681.774967] [<ffffffffa95d2810>] dump_stack+0x4c/0x7f [ 681.774970] [<ffffffffa91a44f4>] report_size_overflow+0x34/0x50 [ 681.774972] [<ffffffffa94d17e2>] qdisc_tree_decrease_qlen+0x152/0x160 [ 681.774976] [<ffffffffc02694b1>] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel] [ 681.774978] [<ffffffffc02680a0>] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel] [ 681.774980] [<ffffffffa94cd92d>] __qdisc_run+0x4d/0x1d0 [ 681.774983] [<ffffffffa949b2b2>] net_tx_action+0xc2/0x160 [ 681.774985] [<ffffffffa90664c1>] __do_softirq+0xf1/0x200 [ 681.774987] [<ffffffffa90665ee>] run_ksoftirqd+0x1e/0x30 [ 681.774989] [<ffffffffa90896b0>] smpboot_thread_fn+0x150/0x260 [ 681.774991] [<ffffffffa9089560>] ? sort_range+0x40/0x40 [ 681.774992] [<ffffffffa9085fe4>] kthread+0xe4/0x100 [ 681.774994] [<ffffffffa9085f00>] ? kthread_worker_fn+0x170/0x170 [ 681.774995] [<ffffffffa95d8d1e>] ret_from_fork+0x3e/0x70 mq/mqprio have their own ways to report qlen/drops by folding stats on all their queues, with appropriate locking. A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup() without proper locking : concurrent qdisc updates could corrupt the list that qdisc_match_from_root() parses to find a qdisc given its handle. Fix first problem adding a TCQ_F_NOPARENT qdisc flag that qdisc_tree_decrease_qlen() can use to abort its tree traversal, as soon as it meets a mq/mqprio qdisc children. Second problem can be fixed by RCU protection. Qdisc are already freed after RCU grace period, so qdisc_list_add() and qdisc_list_del() simply have to use appropriate rcu list variants. A future patch will add a per struct netdev_queue list anchor, so that qdisc_tree_decrease_qlen() can have more efficient lookups. Reported-by: Daniele Fucini <dfucini@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <cwang@twopensource.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-02 11:08:51 +07:00
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
sch->flags |= TCQ_F_MQROOT;
return 0;
err:
mq_destroy(sch);
return -ENOMEM;
}
static void mq_attach(struct Qdisc *sch)
{
struct net_device *dev = qdisc_dev(sch);
struct mq_sched *priv = qdisc_priv(sch);
struct Qdisc *qdisc, *old;
unsigned int ntx;
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
qdisc = priv->qdiscs[ntx];
old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
if (old)
qdisc_destroy(old);
#ifdef CONFIG_NET_SCHED
if (ntx < dev->real_num_tx_queues)
qdisc_hash_add(qdisc);
#endif
}
kfree(priv->qdiscs);
priv->qdiscs = NULL;
}
static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct net_device *dev = qdisc_dev(sch);
struct Qdisc *qdisc;
unsigned int ntx;
sch->q.qlen = 0;
memset(&sch->bstats, 0, sizeof(sch->bstats));
memset(&sch->qstats, 0, sizeof(sch->qstats));
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
spin_lock_bh(qdisc_lock(qdisc));
sch->q.qlen += qdisc->q.qlen;
sch->bstats.bytes += qdisc->bstats.bytes;
sch->bstats.packets += qdisc->bstats.packets;
sch->qstats.backlog += qdisc->qstats.backlog;
sch->qstats.drops += qdisc->qstats.drops;
sch->qstats.requeues += qdisc->qstats.requeues;
sch->qstats.overlimits += qdisc->qstats.overlimits;
spin_unlock_bh(qdisc_lock(qdisc));
}
return 0;
}
static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl)
{
struct net_device *dev = qdisc_dev(sch);
unsigned long ntx = cl - 1;
if (ntx >= dev->num_tx_queues)
return NULL;
return netdev_get_tx_queue(dev, ntx);
}
static struct netdev_queue *mq_select_queue(struct Qdisc *sch,
struct tcmsg *tcm)
{
unsigned int ntx = TC_H_MIN(tcm->tcm_parent);
struct netdev_queue *dev_queue = mq_queue_get(sch, ntx);
if (!dev_queue) {
struct net_device *dev = qdisc_dev(sch);
return netdev_get_tx_queue(dev, 0);
}
return dev_queue;
}
static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
struct Qdisc **old)
{
struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
struct net_device *dev = qdisc_dev(sch);
if (dev->flags & IFF_UP)
dev_deactivate(dev);
*old = dev_graft_qdisc(dev_queue, new);
if (new)
net_sched: fix qdisc_tree_decrease_qlen() races qdisc_tree_decrease_qlen() suffers from two problems on multiqueue devices. One problem is that it updates sch->q.qlen and sch->qstats.drops on the mq/mqprio root qdisc, while it should not : Daniele reported underflows errors : [ 681.774821] PAX: sch->q.qlen: 0 n: 1 [ 681.774825] PAX: size overflow detected in function qdisc_tree_decrease_qlen net/sched/sch_api.c:769 cicus.693_49 min, count: 72, decl: qlen; num: 0; context: sk_buff_head; [ 681.774954] CPU: 2 PID: 19 Comm: ksoftirqd/2 Tainted: G O 4.2.6.201511282239-1-grsec #1 [ 681.774955] Hardware name: ASUSTeK COMPUTER INC. X302LJ/X302LJ, BIOS X302LJ.202 03/05/2015 [ 681.774956] ffffffffa9a04863 0000000000000000 0000000000000000 ffffffffa990ff7c [ 681.774959] ffffc90000d3bc38 ffffffffa95d2810 0000000000000007 ffffffffa991002b [ 681.774960] ffffc90000d3bc68 ffffffffa91a44f4 0000000000000001 0000000000000001 [ 681.774962] Call Trace: [ 681.774967] [<ffffffffa95d2810>] dump_stack+0x4c/0x7f [ 681.774970] [<ffffffffa91a44f4>] report_size_overflow+0x34/0x50 [ 681.774972] [<ffffffffa94d17e2>] qdisc_tree_decrease_qlen+0x152/0x160 [ 681.774976] [<ffffffffc02694b1>] fq_codel_dequeue+0x7b1/0x820 [sch_fq_codel] [ 681.774978] [<ffffffffc02680a0>] ? qdisc_peek_dequeued+0xa0/0xa0 [sch_fq_codel] [ 681.774980] [<ffffffffa94cd92d>] __qdisc_run+0x4d/0x1d0 [ 681.774983] [<ffffffffa949b2b2>] net_tx_action+0xc2/0x160 [ 681.774985] [<ffffffffa90664c1>] __do_softirq+0xf1/0x200 [ 681.774987] [<ffffffffa90665ee>] run_ksoftirqd+0x1e/0x30 [ 681.774989] [<ffffffffa90896b0>] smpboot_thread_fn+0x150/0x260 [ 681.774991] [<ffffffffa9089560>] ? sort_range+0x40/0x40 [ 681.774992] [<ffffffffa9085fe4>] kthread+0xe4/0x100 [ 681.774994] [<ffffffffa9085f00>] ? kthread_worker_fn+0x170/0x170 [ 681.774995] [<ffffffffa95d8d1e>] ret_from_fork+0x3e/0x70 mq/mqprio have their own ways to report qlen/drops by folding stats on all their queues, with appropriate locking. A second problem is that qdisc_tree_decrease_qlen() calls qdisc_lookup() without proper locking : concurrent qdisc updates could corrupt the list that qdisc_match_from_root() parses to find a qdisc given its handle. Fix first problem adding a TCQ_F_NOPARENT qdisc flag that qdisc_tree_decrease_qlen() can use to abort its tree traversal, as soon as it meets a mq/mqprio qdisc children. Second problem can be fixed by RCU protection. Qdisc are already freed after RCU grace period, so qdisc_list_add() and qdisc_list_del() simply have to use appropriate rcu list variants. A future patch will add a per struct netdev_queue list anchor, so that qdisc_tree_decrease_qlen() can have more efficient lookups. Reported-by: Daniele Fucini <dfucini@gmail.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <cwang@twopensource.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-02 11:08:51 +07:00
new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
dev_activate(dev);
return 0;
}
static struct Qdisc *mq_leaf(struct Qdisc *sch, unsigned long cl)
{
struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
return dev_queue->qdisc_sleeping;
}
static unsigned long mq_get(struct Qdisc *sch, u32 classid)
{
unsigned int ntx = TC_H_MIN(classid);
if (!mq_queue_get(sch, ntx))
return 0;
return ntx;
}
static void mq_put(struct Qdisc *sch, unsigned long cl)
{
}
static int mq_dump_class(struct Qdisc *sch, unsigned long cl,
struct sk_buff *skb, struct tcmsg *tcm)
{
struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
tcm->tcm_parent = TC_H_ROOT;
tcm->tcm_handle |= TC_H_MIN(cl);
tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
return 0;
}
static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
struct gnet_dump *d)
{
struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
sch = dev_queue->qdisc_sleeping;
if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 ||
gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0)
return -1;
return 0;
}
static void mq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
struct net_device *dev = qdisc_dev(sch);
unsigned int ntx;
if (arg->stop)
return;
arg->count = arg->skip;
for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) {
if (arg->fn(sch, ntx + 1, arg) < 0) {
arg->stop = 1;
break;
}
arg->count++;
}
}
static const struct Qdisc_class_ops mq_class_ops = {
.select_queue = mq_select_queue,
.graft = mq_graft,
.leaf = mq_leaf,
.get = mq_get,
.put = mq_put,
.walk = mq_walk,
.dump = mq_dump_class,
.dump_stats = mq_dump_class_stats,
};
struct Qdisc_ops mq_qdisc_ops __read_mostly = {
.cl_ops = &mq_class_ops,
.id = "mq",
.priv_size = sizeof(struct mq_sched),
.init = mq_init,
.destroy = mq_destroy,
.attach = mq_attach,
.dump = mq_dump,
.owner = THIS_MODULE,
};