linux/net/sched/sch_mq.c

276 lines
6.7 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* net/sched/sch_mq.c Classful multiqueue dummy scheduler
*
* Copyright (c) 2009 Patrick McHardy <kaber@trash.net>
*/
#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 08:04:11 +00:00
#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_cls.h>
#include <net/pkt_sched.h>
#include <net/sch_generic.h>
struct mq_sched {
struct Qdisc **qdiscs;
};
static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd)
{
struct net_device *dev = qdisc_dev(sch);
struct tc_mq_qopt_offload opt = {
.command = cmd,
.handle = sch->handle,
};
if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
return -EOPNOTSUPP;
return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt);
}
static int mq_offload_stats(struct Qdisc *sch)
{
struct tc_mq_qopt_offload opt = {
.command = TC_MQ_STATS,
.handle = sch->handle,
.stats = {
.bstats = &sch->bstats,
.qstats = &sch->qstats,
},
};
return qdisc_offload_dump_helper(sch, TC_SETUP_QDISC_MQ, &opt);
}
static void mq_destroy(struct Qdisc *sch)
{
struct net_device *dev = qdisc_dev(sch);
struct mq_sched *priv = qdisc_priv(sch);
unsigned int ntx;
mq_offload(sch, TC_MQ_DESTROY);
if (!priv->qdiscs)
return;
for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
qdisc_put(priv->qdiscs[ntx]);
kfree(priv->qdiscs);
}
static int mq_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
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);
net_sched: fix error recovery at qdisc creation Dmitry reported uses after free in qdisc code [1] The problem here is that ops->init() can return an error. qdisc_create_dflt() then call ops->destroy(), while qdisc_create() does _not_ call it. Four qdisc chose to call their own ops->destroy(), assuming their caller would not. This patch makes sure qdisc_create() calls ops->destroy() and fixes the four qdisc to avoid double free. [1] BUG: KASAN: use-after-free in mq_destroy+0x242/0x290 net/sched/sch_mq.c:33 at addr ffff8801d415d440 Read of size 8 by task syz-executor2/5030 CPU: 0 PID: 5030 Comm: syz-executor2 Not tainted 4.3.5-smp-DEV #119 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 0000000000000046 ffff8801b435b870 ffffffff81bbbed4 ffff8801db000400 ffff8801d415d440 ffff8801d415dc40 ffff8801c4988510 ffff8801b435b898 ffffffff816682b1 ffff8801b435b928 ffff8801d415d440 ffff8801c49880c0 Call Trace: [<ffffffff81bbbed4>] __dump_stack lib/dump_stack.c:15 [inline] [<ffffffff81bbbed4>] dump_stack+0x6c/0x98 lib/dump_stack.c:51 [<ffffffff816682b1>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158 [<ffffffff81668524>] print_address_description mm/kasan/report.c:196 [inline] [<ffffffff81668524>] kasan_report_error+0x1b4/0x4b0 mm/kasan/report.c:285 [<ffffffff81668953>] kasan_report mm/kasan/report.c:305 [inline] [<ffffffff81668953>] __asan_report_load8_noabort+0x43/0x50 mm/kasan/report.c:326 [<ffffffff82527b02>] mq_destroy+0x242/0x290 net/sched/sch_mq.c:33 [<ffffffff82524bdd>] qdisc_destroy+0x12d/0x290 net/sched/sch_generic.c:953 [<ffffffff82524e30>] qdisc_create_dflt+0xf0/0x120 net/sched/sch_generic.c:848 [<ffffffff8252550d>] attach_default_qdiscs net/sched/sch_generic.c:1029 [inline] [<ffffffff8252550d>] dev_activate+0x6ad/0x880 net/sched/sch_generic.c:1064 [<ffffffff824b1db1>] __dev_open+0x221/0x320 net/core/dev.c:1403 [<ffffffff824b24ce>] __dev_change_flags+0x15e/0x3e0 net/core/dev.c:6858 [<ffffffff824b27de>] dev_change_flags+0x8e/0x140 net/core/dev.c:6926 [<ffffffff824f5bf6>] dev_ifsioc+0x446/0x890 net/core/dev_ioctl.c:260 [<ffffffff824f61fa>] dev_ioctl+0x1ba/0xb80 net/core/dev_ioctl.c:546 [<ffffffff82430509>] sock_do_ioctl+0x99/0xb0 net/socket.c:879 [<ffffffff82430d30>] sock_ioctl+0x2a0/0x390 net/socket.c:958 [<ffffffff816f3b68>] vfs_ioctl fs/ioctl.c:44 [inline] [<ffffffff816f3b68>] do_vfs_ioctl+0x8a8/0xe50 fs/ioctl.c:611 [<ffffffff816f41a4>] SYSC_ioctl fs/ioctl.c:626 [inline] [<ffffffff816f41a4>] SyS_ioctl+0x94/0xc0 fs/ioctl.c:617 [<ffffffff8123e357>] entry_SYSCALL_64_fastpath+0x12/0x17 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-10 18:31:49 +00:00
if (!priv->qdiscs)
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)),
extack);
net_sched: fix error recovery at qdisc creation Dmitry reported uses after free in qdisc code [1] The problem here is that ops->init() can return an error. qdisc_create_dflt() then call ops->destroy(), while qdisc_create() does _not_ call it. Four qdisc chose to call their own ops->destroy(), assuming their caller would not. This patch makes sure qdisc_create() calls ops->destroy() and fixes the four qdisc to avoid double free. [1] BUG: KASAN: use-after-free in mq_destroy+0x242/0x290 net/sched/sch_mq.c:33 at addr ffff8801d415d440 Read of size 8 by task syz-executor2/5030 CPU: 0 PID: 5030 Comm: syz-executor2 Not tainted 4.3.5-smp-DEV #119 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 0000000000000046 ffff8801b435b870 ffffffff81bbbed4 ffff8801db000400 ffff8801d415d440 ffff8801d415dc40 ffff8801c4988510 ffff8801b435b898 ffffffff816682b1 ffff8801b435b928 ffff8801d415d440 ffff8801c49880c0 Call Trace: [<ffffffff81bbbed4>] __dump_stack lib/dump_stack.c:15 [inline] [<ffffffff81bbbed4>] dump_stack+0x6c/0x98 lib/dump_stack.c:51 [<ffffffff816682b1>] kasan_object_err+0x21/0x70 mm/kasan/report.c:158 [<ffffffff81668524>] print_address_description mm/kasan/report.c:196 [inline] [<ffffffff81668524>] kasan_report_error+0x1b4/0x4b0 mm/kasan/report.c:285 [<ffffffff81668953>] kasan_report mm/kasan/report.c:305 [inline] [<ffffffff81668953>] __asan_report_load8_noabort+0x43/0x50 mm/kasan/report.c:326 [<ffffffff82527b02>] mq_destroy+0x242/0x290 net/sched/sch_mq.c:33 [<ffffffff82524bdd>] qdisc_destroy+0x12d/0x290 net/sched/sch_generic.c:953 [<ffffffff82524e30>] qdisc_create_dflt+0xf0/0x120 net/sched/sch_generic.c:848 [<ffffffff8252550d>] attach_default_qdiscs net/sched/sch_generic.c:1029 [inline] [<ffffffff8252550d>] dev_activate+0x6ad/0x880 net/sched/sch_generic.c:1064 [<ffffffff824b1db1>] __dev_open+0x221/0x320 net/core/dev.c:1403 [<ffffffff824b24ce>] __dev_change_flags+0x15e/0x3e0 net/core/dev.c:6858 [<ffffffff824b27de>] dev_change_flags+0x8e/0x140 net/core/dev.c:6926 [<ffffffff824f5bf6>] dev_ifsioc+0x446/0x890 net/core/dev_ioctl.c:260 [<ffffffff824f61fa>] dev_ioctl+0x1ba/0xb80 net/core/dev_ioctl.c:546 [<ffffffff82430509>] sock_do_ioctl+0x99/0xb0 net/socket.c:879 [<ffffffff82430d30>] sock_ioctl+0x2a0/0x390 net/socket.c:958 [<ffffffff816f3b68>] vfs_ioctl fs/ioctl.c:44 [inline] [<ffffffff816f3b68>] do_vfs_ioctl+0x8a8/0xe50 fs/ioctl.c:611 [<ffffffff816f41a4>] SYSC_ioctl fs/ioctl.c:626 [inline] [<ffffffff816f41a4>] SyS_ioctl+0x94/0xc0 fs/ioctl.c:617 [<ffffffff8123e357>] entry_SYSCALL_64_fastpath+0x12/0x17 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-02-10 18:31:49 +00:00
if (!qdisc)
return -ENOMEM;
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 04:08:51 +00:00
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
sch->flags |= TCQ_F_MQROOT;
mq_offload(sch, TC_MQ_CREATE);
return 0;
}
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_put(old);
#ifdef CONFIG_NET_SCHED
if (ntx < dev->real_num_tx_queues)
qdisc_hash_add(qdisc, false);
#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;
gnet_stats_basic_sync_init(&sch->bstats);
memset(&sch->qstats, 0, sizeof(sch->qstats));
/* MQ supports lockless qdiscs. However, statistics accounting needs
* to account for all, none, or a mix of locked and unlocked child
* qdiscs. Percpu stats are added to counters in-band and locking
* qdisc totals are added at end.
*/
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
spin_lock_bh(qdisc_lock(qdisc));
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
gnet_stats_add_basic(&sch->bstats, qdisc->cpu_bstats,
&qdisc->bstats, false);
gnet_stats_add_queue(&sch->qstats, qdisc->cpu_qstats,
&qdisc->qstats);
sch->q.qlen += qdisc_qlen(qdisc);
spin_unlock_bh(qdisc_lock(qdisc));
}
return mq_offload_stats(sch);
}
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)
{
return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
}
static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
struct Qdisc **old, struct netlink_ext_ack *extack)
{
struct netdev_queue *dev_queue = mq_queue_get(sch, cl);
struct tc_mq_qopt_offload graft_offload;
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 04:08:51 +00:00
new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
dev_activate(dev);
graft_offload.handle = sch->handle;
graft_offload.graft_params.queue = cl - 1;
graft_offload.graft_params.child_handle = new ? new->handle : 0;
graft_offload.command = TC_MQ_GRAFT;
qdisc_offload_graft_helper(qdisc_dev(sch), sch, new, *old,
TC_SETUP_QDISC_MQ, &graft_offload, extack);
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_find(struct Qdisc *sch, u32 classid)
{
unsigned int ntx = TC_H_MIN(classid);
if (!mq_queue_get(sch, ntx))
return 0;
return ntx;
}
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;
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, sch->cpu_bstats, &sch->bstats, true) < 0 ||
qdisc_qstats_copy(d, sch) < 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 (!tc_qdisc_stats_dump(sch, ntx + 1, arg))
break;
}
}
static const struct Qdisc_class_ops mq_class_ops = {
.select_queue = mq_select_queue,
.graft = mq_graft,
.leaf = mq_leaf,
.find = mq_find,
.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,
.change_real_num_tx = mq_change_real_num_tx,
.dump = mq_dump,
.owner = THIS_MODULE,
};