linux-stable/net/sched/sch_generic.c

1605 lines
38 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-or-later
/*
* net/sched/sch_generic.c Generic packet scheduler routines.
*
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
* Jamal Hadi Salim, <hadi@cyberus.ca> 990601
* - Ingress support
*/
#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/rcupdate.h>
#include <linux/list.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/if_vlan.h>
#include <linux/skb_array.h>
#include <linux/if_macvlan.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
#include <trace/events/qdisc.h>
#include <trace/events/net.h>
#include <net/xfrm.h>
/* Qdisc to use by default */
const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
EXPORT_SYMBOL(default_qdisc_ops);
static void qdisc_maybe_clear_missed(struct Qdisc *q,
const struct netdev_queue *txq)
{
clear_bit(__QDISC_STATE_MISSED, &q->state);
/* Make sure the below netif_xmit_frozen_or_stopped()
* checking happens after clearing STATE_MISSED.
*/
smp_mb__after_atomic();
/* Checking netif_xmit_frozen_or_stopped() again to
* make sure STATE_MISSED is set if the STATE_MISSED
* set by netif_tx_wake_queue()'s rescheduling of
* net_tx_action() is cleared by the above clear_bit().
*/
if (!netif_xmit_frozen_or_stopped(txq))
set_bit(__QDISC_STATE_MISSED, &q->state);
net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK flag set, but queue discipline by-pass does not work for lockless qdisc because skb is always enqueued to qdisc even when the qdisc is empty, see __dev_xmit_skb(). This patch calls sch_direct_xmit() to transmit the skb directly to the driver for empty lockless qdisc, which aviod enqueuing and dequeuing operation. As qdisc->empty is not reliable to indicate a empty qdisc because there is a time window between enqueuing and setting qdisc->empty. So we use the MISSED state added in commit a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc"), which indicate there is lock contention, suggesting that it is better not to do the qdisc bypass in order to avoid packet out of order problem. In order to make MISSED state reliable to indicate a empty qdisc, we need to ensure that testing and clearing of MISSED state is within the protection of qdisc->seqlock, only setting MISSED state can be done without the protection of qdisc->seqlock. A MISSED state testing is added without the protection of qdisc->seqlock to aviod doing unnecessary spin_trylock() for contention case. As the enqueuing is not within the protection of qdisc->seqlock, there is still a potential data race as mentioned by Jakub [1]: thread1 thread2 thread3 qdisc_run_begin() # true qdisc_run_begin(q) set(MISSED) pfifo_fast_dequeue clear(MISSED) # recheck the queue qdisc_run_end() enqueue skb1 qdisc empty # true qdisc_run_begin() # true sch_direct_xmit() # skb2 qdisc_run_begin() set(MISSED) When above happens, skb1 enqueued by thread2 is transmited after skb2 is transmited by thread3 because MISSED state setting and enqueuing is not under the qdisc->seqlock. If qdisc bypass is disabled, skb1 has better chance to be transmited quicker than skb2. This patch does not take care of the above data race, because we view this as similar as below: Even at the same time CPU1 and CPU2 write the skb to two socket which both heading to the same qdisc, there is no guarantee that which skb will hit the qdisc first, because there is a lot of factor like interrupt/softirq/cache miss/scheduling afffecting that. There are below cases that need special handling: 1. When MISSED state is cleared before another round of dequeuing in pfifo_fast_dequeue(), and __qdisc_run() might not be able to dequeue all skb in one round and call __netif_schedule(), which might result in a non-empty qdisc without MISSED set. In order to avoid this, the MISSED state is set for lockless qdisc and __netif_schedule() will be called at the end of qdisc_run_end. 2. The MISSED state also need to be set for lockless qdisc instead of calling __netif_schedule() directly when requeuing a skb for a similar reason. 3. For netdev queue stopped case, the MISSED case need clearing while the netdev queue is stopped, otherwise there may be unnecessary __netif_schedule() calling. So a new DRAINING state is added to indicate this case, which also indicate a non-empty qdisc. 4. As there is already netif_xmit_frozen_or_stopped() checking in dequeue_skb() and sch_direct_xmit(), which are both within the protection of qdisc->seqlock, but the same checking in __dev_xmit_skb() is without the protection, which might cause empty indication of a lockless qdisc to be not reliable. So remove the checking in __dev_xmit_skb(), and the checking in the protection of qdisc->seqlock seems enough to avoid the cpu consumption problem for netdev queue stopped case. 1. https://lkml.org/lkml/2021/5/29/215 Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 06:49:56 +00:00
else
set_bit(__QDISC_STATE_DRAINING, &q->state);
}
/* Main transmission queue. */
/* Modifications to data participating in scheduling must be protected with
* qdisc_lock(qdisc) spinlock.
*
* The idea is the following:
* - enqueue, dequeue are serialized via qdisc root lock
* - ingress filtering is also serialized via qdisc root lock
* - updates to tree and tree walking are only done under the rtnl mutex.
*/
net: sched: fix reordering issues Whenever MQ is not used on a multiqueue device, we experience serious reordering problems. Bisection found the cited commit. The issue can be described this way : - A single qdisc hierarchy is shared by all transmit queues. (eg : tc qdisc replace dev eth0 root fq_codel) - When/if try_bulk_dequeue_skb_slow() dequeues a packet targetting a different transmit queue than the one used to build a packet train, we stop building the current list and save the 'bad' skb (P1) in a special queue. (bad_txq) - When dequeue_skb() calls qdisc_dequeue_skb_bad_txq() and finds this skb (P1), it checks if the associated transmit queues is still in frozen state. If the queue is still blocked (by BQL or NIC tx ring full), we leave the skb in bad_txq and return NULL. - dequeue_skb() calls q->dequeue() to get another packet (P2) The other packet can target the problematic queue (that we found in frozen state for the bad_txq packet), but another cpu just ran TX completion and made room in the txq that is now ready to accept new packets. - Packet P2 is sent while P1 is still held in bad_txq, P1 might be sent at next round. In practice P2 is the lead of a big packet train (P2,P3,P4 ...) filling the BQL budget and delaying P1 by many packets :/ To solve this problem, we have to block the dequeue process as long as the first packet in bad_txq can not be sent. Reordering issues disappear and no side effects have been seen. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.fastabend@gmail.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-05 12:20:22 +00:00
#define SKB_XOFF_MAGIC ((struct sk_buff *)1UL)
static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q)
{
const struct netdev_queue *txq = q->dev_queue;
spinlock_t *lock = NULL;
struct sk_buff *skb;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
skb = skb_peek(&q->skb_bad_txq);
if (skb) {
/* check the reason of requeuing without tx lock first */
txq = skb_get_tx_queue(txq->dev, skb);
if (!netif_xmit_frozen_or_stopped(txq)) {
skb = __skb_dequeue(&q->skb_bad_txq);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_dec(q, skb);
qdisc_qstats_cpu_qlen_dec(q);
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
}
} else {
net: sched: fix reordering issues Whenever MQ is not used on a multiqueue device, we experience serious reordering problems. Bisection found the cited commit. The issue can be described this way : - A single qdisc hierarchy is shared by all transmit queues. (eg : tc qdisc replace dev eth0 root fq_codel) - When/if try_bulk_dequeue_skb_slow() dequeues a packet targetting a different transmit queue than the one used to build a packet train, we stop building the current list and save the 'bad' skb (P1) in a special queue. (bad_txq) - When dequeue_skb() calls qdisc_dequeue_skb_bad_txq() and finds this skb (P1), it checks if the associated transmit queues is still in frozen state. If the queue is still blocked (by BQL or NIC tx ring full), we leave the skb in bad_txq and return NULL. - dequeue_skb() calls q->dequeue() to get another packet (P2) The other packet can target the problematic queue (that we found in frozen state for the bad_txq packet), but another cpu just ran TX completion and made room in the txq that is now ready to accept new packets. - Packet P2 is sent while P1 is still held in bad_txq, P1 might be sent at next round. In practice P2 is the lead of a big packet train (P2,P3,P4 ...) filling the BQL budget and delaying P1 by many packets :/ To solve this problem, we have to block the dequeue process as long as the first packet in bad_txq can not be sent. Reordering issues disappear and no side effects have been seen. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.fastabend@gmail.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-05 12:20:22 +00:00
skb = SKB_XOFF_MAGIC;
qdisc_maybe_clear_missed(q, txq);
}
}
if (lock)
spin_unlock(lock);
return skb;
}
static inline struct sk_buff *qdisc_dequeue_skb_bad_txq(struct Qdisc *q)
{
struct sk_buff *skb = skb_peek(&q->skb_bad_txq);
if (unlikely(skb))
skb = __skb_dequeue_bad_txq(q);
return skb;
}
static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q,
struct sk_buff *skb)
{
spinlock_t *lock = NULL;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
__skb_queue_tail(&q->skb_bad_txq, skb);
net: sched: fix uses after free syzbot reported one use-after-free in pfifo_fast_enqueue() [1] Issue here is that we can not reuse skb after a successful skb_array_produce() since another cpu might have consumed it already. I believe a similar problem exists in try_bulk_dequeue_skb_slow() in case we put an skb into qdisc_enqueue_skb_bad_txq() for lockless qdisc. [1] BUG: KASAN: use-after-free in qdisc_pkt_len include/net/sch_generic.h:610 [inline] BUG: KASAN: use-after-free in qdisc_qstats_cpu_backlog_inc include/net/sch_generic.h:712 [inline] BUG: KASAN: use-after-free in pfifo_fast_enqueue+0x4bc/0x5e0 net/sched/sch_generic.c:639 Read of size 4 at addr ffff8801cede37e8 by task syzkaller717588/5543 CPU: 1 PID: 5543 Comm: syzkaller717588 Not tainted 4.16.0-rc4+ #265 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x24d lib/dump_stack.c:53 print_address_description+0x73/0x250 mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report+0x23c/0x360 mm/kasan/report.c:412 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:432 qdisc_pkt_len include/net/sch_generic.h:610 [inline] qdisc_qstats_cpu_backlog_inc include/net/sch_generic.h:712 [inline] pfifo_fast_enqueue+0x4bc/0x5e0 net/sched/sch_generic.c:639 __dev_xmit_skb net/core/dev.c:3216 [inline] Fixes: c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot+ed43b6903ab968b16f54@syzkaller.appspotmail.com Cc: John Fastabend <john.fastabend@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-15 01:53:00 +00:00
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_inc(q, skb);
qdisc_qstats_cpu_qlen_inc(q);
net: sched: fix uses after free syzbot reported one use-after-free in pfifo_fast_enqueue() [1] Issue here is that we can not reuse skb after a successful skb_array_produce() since another cpu might have consumed it already. I believe a similar problem exists in try_bulk_dequeue_skb_slow() in case we put an skb into qdisc_enqueue_skb_bad_txq() for lockless qdisc. [1] BUG: KASAN: use-after-free in qdisc_pkt_len include/net/sch_generic.h:610 [inline] BUG: KASAN: use-after-free in qdisc_qstats_cpu_backlog_inc include/net/sch_generic.h:712 [inline] BUG: KASAN: use-after-free in pfifo_fast_enqueue+0x4bc/0x5e0 net/sched/sch_generic.c:639 Read of size 4 at addr ffff8801cede37e8 by task syzkaller717588/5543 CPU: 1 PID: 5543 Comm: syzkaller717588 Not tainted 4.16.0-rc4+ #265 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x24d lib/dump_stack.c:53 print_address_description+0x73/0x250 mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report+0x23c/0x360 mm/kasan/report.c:412 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:432 qdisc_pkt_len include/net/sch_generic.h:610 [inline] qdisc_qstats_cpu_backlog_inc include/net/sch_generic.h:712 [inline] pfifo_fast_enqueue+0x4bc/0x5e0 net/sched/sch_generic.c:639 __dev_xmit_skb net/core/dev.c:3216 [inline] Fixes: c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot+ed43b6903ab968b16f54@syzkaller.appspotmail.com Cc: John Fastabend <john.fastabend@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-15 01:53:00 +00:00
} else {
qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++;
}
if (lock)
spin_unlock(lock);
}
static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
{
spinlock_t *lock = NULL;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
while (skb) {
struct sk_buff *next = skb->next;
__skb_queue_tail(&q->gso_skb, skb);
/* it's still part of the queue */
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_requeues_inc(q);
qdisc_qstats_cpu_backlog_inc(q, skb);
qdisc_qstats_cpu_qlen_inc(q);
} else {
q->qstats.requeues++;
qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++;
}
skb = next;
}
net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK flag set, but queue discipline by-pass does not work for lockless qdisc because skb is always enqueued to qdisc even when the qdisc is empty, see __dev_xmit_skb(). This patch calls sch_direct_xmit() to transmit the skb directly to the driver for empty lockless qdisc, which aviod enqueuing and dequeuing operation. As qdisc->empty is not reliable to indicate a empty qdisc because there is a time window between enqueuing and setting qdisc->empty. So we use the MISSED state added in commit a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc"), which indicate there is lock contention, suggesting that it is better not to do the qdisc bypass in order to avoid packet out of order problem. In order to make MISSED state reliable to indicate a empty qdisc, we need to ensure that testing and clearing of MISSED state is within the protection of qdisc->seqlock, only setting MISSED state can be done without the protection of qdisc->seqlock. A MISSED state testing is added without the protection of qdisc->seqlock to aviod doing unnecessary spin_trylock() for contention case. As the enqueuing is not within the protection of qdisc->seqlock, there is still a potential data race as mentioned by Jakub [1]: thread1 thread2 thread3 qdisc_run_begin() # true qdisc_run_begin(q) set(MISSED) pfifo_fast_dequeue clear(MISSED) # recheck the queue qdisc_run_end() enqueue skb1 qdisc empty # true qdisc_run_begin() # true sch_direct_xmit() # skb2 qdisc_run_begin() set(MISSED) When above happens, skb1 enqueued by thread2 is transmited after skb2 is transmited by thread3 because MISSED state setting and enqueuing is not under the qdisc->seqlock. If qdisc bypass is disabled, skb1 has better chance to be transmited quicker than skb2. This patch does not take care of the above data race, because we view this as similar as below: Even at the same time CPU1 and CPU2 write the skb to two socket which both heading to the same qdisc, there is no guarantee that which skb will hit the qdisc first, because there is a lot of factor like interrupt/softirq/cache miss/scheduling afffecting that. There are below cases that need special handling: 1. When MISSED state is cleared before another round of dequeuing in pfifo_fast_dequeue(), and __qdisc_run() might not be able to dequeue all skb in one round and call __netif_schedule(), which might result in a non-empty qdisc without MISSED set. In order to avoid this, the MISSED state is set for lockless qdisc and __netif_schedule() will be called at the end of qdisc_run_end. 2. The MISSED state also need to be set for lockless qdisc instead of calling __netif_schedule() directly when requeuing a skb for a similar reason. 3. For netdev queue stopped case, the MISSED case need clearing while the netdev queue is stopped, otherwise there may be unnecessary __netif_schedule() calling. So a new DRAINING state is added to indicate this case, which also indicate a non-empty qdisc. 4. As there is already netif_xmit_frozen_or_stopped() checking in dequeue_skb() and sch_direct_xmit(), which are both within the protection of qdisc->seqlock, but the same checking in __dev_xmit_skb() is without the protection, which might cause empty indication of a lockless qdisc to be not reliable. So remove the checking in __dev_xmit_skb(), and the checking in the protection of qdisc->seqlock seems enough to avoid the cpu consumption problem for netdev queue stopped case. 1. https://lkml.org/lkml/2021/5/29/215 Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 06:49:56 +00:00
if (lock) {
spin_unlock(lock);
net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK flag set, but queue discipline by-pass does not work for lockless qdisc because skb is always enqueued to qdisc even when the qdisc is empty, see __dev_xmit_skb(). This patch calls sch_direct_xmit() to transmit the skb directly to the driver for empty lockless qdisc, which aviod enqueuing and dequeuing operation. As qdisc->empty is not reliable to indicate a empty qdisc because there is a time window between enqueuing and setting qdisc->empty. So we use the MISSED state added in commit a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc"), which indicate there is lock contention, suggesting that it is better not to do the qdisc bypass in order to avoid packet out of order problem. In order to make MISSED state reliable to indicate a empty qdisc, we need to ensure that testing and clearing of MISSED state is within the protection of qdisc->seqlock, only setting MISSED state can be done without the protection of qdisc->seqlock. A MISSED state testing is added without the protection of qdisc->seqlock to aviod doing unnecessary spin_trylock() for contention case. As the enqueuing is not within the protection of qdisc->seqlock, there is still a potential data race as mentioned by Jakub [1]: thread1 thread2 thread3 qdisc_run_begin() # true qdisc_run_begin(q) set(MISSED) pfifo_fast_dequeue clear(MISSED) # recheck the queue qdisc_run_end() enqueue skb1 qdisc empty # true qdisc_run_begin() # true sch_direct_xmit() # skb2 qdisc_run_begin() set(MISSED) When above happens, skb1 enqueued by thread2 is transmited after skb2 is transmited by thread3 because MISSED state setting and enqueuing is not under the qdisc->seqlock. If qdisc bypass is disabled, skb1 has better chance to be transmited quicker than skb2. This patch does not take care of the above data race, because we view this as similar as below: Even at the same time CPU1 and CPU2 write the skb to two socket which both heading to the same qdisc, there is no guarantee that which skb will hit the qdisc first, because there is a lot of factor like interrupt/softirq/cache miss/scheduling afffecting that. There are below cases that need special handling: 1. When MISSED state is cleared before another round of dequeuing in pfifo_fast_dequeue(), and __qdisc_run() might not be able to dequeue all skb in one round and call __netif_schedule(), which might result in a non-empty qdisc without MISSED set. In order to avoid this, the MISSED state is set for lockless qdisc and __netif_schedule() will be called at the end of qdisc_run_end. 2. The MISSED state also need to be set for lockless qdisc instead of calling __netif_schedule() directly when requeuing a skb for a similar reason. 3. For netdev queue stopped case, the MISSED case need clearing while the netdev queue is stopped, otherwise there may be unnecessary __netif_schedule() calling. So a new DRAINING state is added to indicate this case, which also indicate a non-empty qdisc. 4. As there is already netif_xmit_frozen_or_stopped() checking in dequeue_skb() and sch_direct_xmit(), which are both within the protection of qdisc->seqlock, but the same checking in __dev_xmit_skb() is without the protection, which might cause empty indication of a lockless qdisc to be not reliable. So remove the checking in __dev_xmit_skb(), and the checking in the protection of qdisc->seqlock seems enough to avoid the cpu consumption problem for netdev queue stopped case. 1. https://lkml.org/lkml/2021/5/29/215 Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 06:49:56 +00:00
set_bit(__QDISC_STATE_MISSED, &q->state);
} else {
__netif_schedule(q);
}
}
static void try_bulk_dequeue_skb(struct Qdisc *q,
struct sk_buff *skb,
net_sched: restore qdisc quota fairness limits after bulk dequeue Restore the quota fairness between qdisc's, that we broke with commit 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"). Before that commit, the quota in __qdisc_run() were in packets as dequeue_skb() would only dequeue a single packet, that assumption broke with bulk dequeue. We choose not to account for the number of packets inside the TSO/GSO packets (accessable via "skb_gso_segs"). As the previous fairness also had this "defect". Thus, GSO/TSO packets counts as a single packet. Further more, we choose to slack on accuracy, by allowing a bulk dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only limited by the BQL bytelimit. This is done because BQL prefers to get its full budget for appropriate feedback from TX completion. In future, we might consider reworking this further and, if it allows, switch to a time-based model, as suggested by Eric. Right now, we only restore old semantics. Joint work with Eric, Hannes, Daniel and Jesper. Hannes wrote the first patch in cooperation with Daniel and Jesper. Eric rewrote the patch. Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 10:18:10 +00:00
const struct netdev_queue *txq,
int *packets)
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-01 20:35:59 +00:00
{
int bytelimit = qdisc_avail_bulklimit(txq) - skb->len;
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-01 20:35:59 +00:00
while (bytelimit > 0) {
struct sk_buff *nskb = q->dequeue(q);
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-01 20:35:59 +00:00
if (!nskb)
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-01 20:35:59 +00:00
break;
bytelimit -= nskb->len; /* covers GSO len */
skb->next = nskb;
skb = nskb;
net_sched: restore qdisc quota fairness limits after bulk dequeue Restore the quota fairness between qdisc's, that we broke with commit 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"). Before that commit, the quota in __qdisc_run() were in packets as dequeue_skb() would only dequeue a single packet, that assumption broke with bulk dequeue. We choose not to account for the number of packets inside the TSO/GSO packets (accessable via "skb_gso_segs"). As the previous fairness also had this "defect". Thus, GSO/TSO packets counts as a single packet. Further more, we choose to slack on accuracy, by allowing a bulk dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only limited by the BQL bytelimit. This is done because BQL prefers to get its full budget for appropriate feedback from TX completion. In future, we might consider reworking this further and, if it allows, switch to a time-based model, as suggested by Eric. Right now, we only restore old semantics. Joint work with Eric, Hannes, Daniel and Jesper. Hannes wrote the first patch in cooperation with Daniel and Jesper. Eric rewrote the patch. Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 10:18:10 +00:00
(*packets)++; /* GSO counts as one pkt */
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-01 20:35:59 +00:00
}
skb_mark_not_on_list(skb);
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-01 20:35:59 +00:00
}
/* This variant of try_bulk_dequeue_skb() makes sure
* all skbs in the chain are for the same txq
*/
static void try_bulk_dequeue_skb_slow(struct Qdisc *q,
struct sk_buff *skb,
int *packets)
{
int mapping = skb_get_queue_mapping(skb);
struct sk_buff *nskb;
int cnt = 0;
do {
nskb = q->dequeue(q);
if (!nskb)
break;
if (unlikely(skb_get_queue_mapping(nskb) != mapping)) {
qdisc_enqueue_skb_bad_txq(q, nskb);
break;
}
skb->next = nskb;
skb = nskb;
} while (++cnt < 8);
(*packets) += cnt;
skb_mark_not_on_list(skb);
}
qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE Based on DaveM's recent API work on dev_hard_start_xmit(), that allows sending/processing an entire skb list. This patch implements qdisc bulk dequeue, by allowing multiple packets to be dequeued in dequeue_skb(). The optimization principle for this is two fold, (1) to amortize locking cost and (2) avoid expensive tailptr update for notifying HW. (1) Several packets are dequeued while holding the qdisc root_lock, amortizing locking cost over several packet. The dequeued SKB list is processed under the TXQ lock in dev_hard_start_xmit(), thus also amortizing the cost of the TXQ lock. (2) Further more, dev_hard_start_xmit() will utilize the skb->xmit_more API to delay HW tailptr update, which also reduces the cost per packet. One restriction of the new API is that every SKB must belong to the same TXQ. This patch takes the easy way out, by restricting bulk dequeue to qdisc's with the TCQ_F_ONETXQUEUE flag, that specifies the qdisc only have attached a single TXQ. Some detail about the flow; dev_hard_start_xmit() will process the skb list, and transmit packets individually towards the driver (see xmit_one()). In case the driver stops midway in the list, the remaining skb list is returned by dev_hard_start_xmit(). In sch_direct_xmit() this returned list is requeued by dev_requeue_skb(). To avoid overshooting the HW limits, which results in requeuing, the patch limits the amount of bytes dequeued, based on the drivers BQL limits. In-effect bulking will only happen for BQL enabled drivers. Small amounts for extra HoL blocking (2x MTU/0.24ms) were measured at 100Mbit/s, with bulking 8 packets, but the oscillating nature of the measurement indicate something, like sched latency might be causing this effect. More comparisons show, that this oscillation goes away occationally. Thus, we disregard this artifact completely and remove any "magic" bulking limit. For now, as a conservative approach, stop bulking when seeing TSO and segmented GSO packets. They already benefit from bulking on their own. A followup patch add this, to allow easier bisect-ability for finding regressions. Jointed work with Hannes, Daniel and Florian. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-01 20:35:59 +00:00
/* Note that dequeue_skb can possibly return a SKB list (via skb->next).
* A requeued skb (via q->gso_skb) can also be a SKB list.
*/
net_sched: restore qdisc quota fairness limits after bulk dequeue Restore the quota fairness between qdisc's, that we broke with commit 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"). Before that commit, the quota in __qdisc_run() were in packets as dequeue_skb() would only dequeue a single packet, that assumption broke with bulk dequeue. We choose not to account for the number of packets inside the TSO/GSO packets (accessable via "skb_gso_segs"). As the previous fairness also had this "defect". Thus, GSO/TSO packets counts as a single packet. Further more, we choose to slack on accuracy, by allowing a bulk dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only limited by the BQL bytelimit. This is done because BQL prefers to get its full budget for appropriate feedback from TX completion. In future, we might consider reworking this further and, if it allows, switch to a time-based model, as suggested by Eric. Right now, we only restore old semantics. Joint work with Eric, Hannes, Daniel and Jesper. Hannes wrote the first patch in cooperation with Daniel and Jesper. Eric rewrote the patch. Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 10:18:10 +00:00
static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
int *packets)
{
const struct netdev_queue *txq = q->dev_queue;
struct sk_buff *skb = NULL;
net_sched: restore qdisc quota fairness limits after bulk dequeue Restore the quota fairness between qdisc's, that we broke with commit 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"). Before that commit, the quota in __qdisc_run() were in packets as dequeue_skb() would only dequeue a single packet, that assumption broke with bulk dequeue. We choose not to account for the number of packets inside the TSO/GSO packets (accessable via "skb_gso_segs"). As the previous fairness also had this "defect". Thus, GSO/TSO packets counts as a single packet. Further more, we choose to slack on accuracy, by allowing a bulk dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only limited by the BQL bytelimit. This is done because BQL prefers to get its full budget for appropriate feedback from TX completion. In future, we might consider reworking this further and, if it allows, switch to a time-based model, as suggested by Eric. Right now, we only restore old semantics. Joint work with Eric, Hannes, Daniel and Jesper. Hannes wrote the first patch in cooperation with Daniel and Jesper. Eric rewrote the patch. Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 10:18:10 +00:00
*packets = 1;
if (unlikely(!skb_queue_empty(&q->gso_skb))) {
spinlock_t *lock = NULL;
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
}
skb = skb_peek(&q->gso_skb);
/* skb may be null if another cpu pulls gso_skb off in between
* empty check and lock.
*/
if (!skb) {
if (lock)
spin_unlock(lock);
goto validate;
}
/* skb in gso_skb were already validated */
*validate = false;
if (xfrm_offload(skb))
*validate = true;
/* check the reason of requeuing without tx lock first */
txq = skb_get_tx_queue(txq->dev, skb);
if (!netif_xmit_frozen_or_stopped(txq)) {
skb = __skb_dequeue(&q->gso_skb);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_dec(q, skb);
qdisc_qstats_cpu_qlen_dec(q);
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
}
} else {
skb = NULL;
qdisc_maybe_clear_missed(q, txq);
}
if (lock)
spin_unlock(lock);
goto trace;
}
validate:
*validate = true;
if ((q->flags & TCQ_F_ONETXQUEUE) &&
netif_xmit_frozen_or_stopped(txq)) {
qdisc_maybe_clear_missed(q, txq);
return skb;
}
skb = qdisc_dequeue_skb_bad_txq(q);
net: sched: fix reordering issues Whenever MQ is not used on a multiqueue device, we experience serious reordering problems. Bisection found the cited commit. The issue can be described this way : - A single qdisc hierarchy is shared by all transmit queues. (eg : tc qdisc replace dev eth0 root fq_codel) - When/if try_bulk_dequeue_skb_slow() dequeues a packet targetting a different transmit queue than the one used to build a packet train, we stop building the current list and save the 'bad' skb (P1) in a special queue. (bad_txq) - When dequeue_skb() calls qdisc_dequeue_skb_bad_txq() and finds this skb (P1), it checks if the associated transmit queues is still in frozen state. If the queue is still blocked (by BQL or NIC tx ring full), we leave the skb in bad_txq and return NULL. - dequeue_skb() calls q->dequeue() to get another packet (P2) The other packet can target the problematic queue (that we found in frozen state for the bad_txq packet), but another cpu just ran TX completion and made room in the txq that is now ready to accept new packets. - Packet P2 is sent while P1 is still held in bad_txq, P1 might be sent at next round. In practice P2 is the lead of a big packet train (P2,P3,P4 ...) filling the BQL budget and delaying P1 by many packets :/ To solve this problem, we have to block the dequeue process as long as the first packet in bad_txq can not be sent. Reordering issues disappear and no side effects have been seen. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.fastabend@gmail.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-05 12:20:22 +00:00
if (unlikely(skb)) {
if (skb == SKB_XOFF_MAGIC)
return NULL;
goto bulk;
net: sched: fix reordering issues Whenever MQ is not used on a multiqueue device, we experience serious reordering problems. Bisection found the cited commit. The issue can be described this way : - A single qdisc hierarchy is shared by all transmit queues. (eg : tc qdisc replace dev eth0 root fq_codel) - When/if try_bulk_dequeue_skb_slow() dequeues a packet targetting a different transmit queue than the one used to build a packet train, we stop building the current list and save the 'bad' skb (P1) in a special queue. (bad_txq) - When dequeue_skb() calls qdisc_dequeue_skb_bad_txq() and finds this skb (P1), it checks if the associated transmit queues is still in frozen state. If the queue is still blocked (by BQL or NIC tx ring full), we leave the skb in bad_txq and return NULL. - dequeue_skb() calls q->dequeue() to get another packet (P2) The other packet can target the problematic queue (that we found in frozen state for the bad_txq packet), but another cpu just ran TX completion and made room in the txq that is now ready to accept new packets. - Packet P2 is sent while P1 is still held in bad_txq, P1 might be sent at next round. In practice P2 is the lead of a big packet train (P2,P3,P4 ...) filling the BQL budget and delaying P1 by many packets :/ To solve this problem, we have to block the dequeue process as long as the first packet in bad_txq can not be sent. Reordering issues disappear and no side effects have been seen. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.fastabend@gmail.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-05 12:20:22 +00:00
}
skb = q->dequeue(q);
if (skb) {
bulk:
if (qdisc_may_bulk(q))
try_bulk_dequeue_skb(q, skb, txq, packets);
else
try_bulk_dequeue_skb_slow(q, skb, packets);
}
trace:
trace_qdisc_dequeue(q, txq, *packets, skb);
return skb;
}
/*
* Transmit possibly several skbs, and handle the return status as
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
* required. Owning qdisc running bit guarantees that only one CPU
* can execute this function.
[NET]: qdisc_restart - readability changes plus one bug fix. New changes : - Incorporated Peter Waskiewicz's comments. - Re-added back one warning message (on driver returning wrong value). Previous changes : - Converted to use switch/case code which looks neater. - "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless check should be removed, since driver will return NETDEV_TX_LOCKED only if lockless is true and driver has to do the locking. In the original code as well as the latest code, this code can result in a bug where if LLTX is not set for a driver (lockless == 0) but the driver is written wrongly to do a trylock (despite LLTX being set), the driver returns LOCKED. But since lockless is zero, the packet is requeue'd instead of calling collision code which will issue warning and free up the skb. Instead this skb will be retried with this driver next time, and the same result will ensue. Removing this check will catch these driver bugs instead of hiding the problem. I am keeping this change to readability section since : a. it is confusing to check two things as it is; and b. it is difficult to keep this check in the changed 'switch' code. - Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is the work being done and easier to understand) and do_dev_requeue to dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to dev_handle_collision (handle_dev_cpu_collision is a small routine with only one caller, so there is no need to have two separate routines which also results in getting rid of two macros, etc. - Removed an XXX comment as it should never fail (I suspect this was related to batch skb WIP, Jamal ?). Converted some functions to original coding style of having the return values and the function name on same line, eg prio2list. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-25 02:56:09 +00:00
*
* Returns to the caller:
* false - hardware queue frozen backoff
* true - feel free to send more pkts
[NET]: qdisc_restart - readability changes plus one bug fix. New changes : - Incorporated Peter Waskiewicz's comments. - Re-added back one warning message (on driver returning wrong value). Previous changes : - Converted to use switch/case code which looks neater. - "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless check should be removed, since driver will return NETDEV_TX_LOCKED only if lockless is true and driver has to do the locking. In the original code as well as the latest code, this code can result in a bug where if LLTX is not set for a driver (lockless == 0) but the driver is written wrongly to do a trylock (despite LLTX being set), the driver returns LOCKED. But since lockless is zero, the packet is requeue'd instead of calling collision code which will issue warning and free up the skb. Instead this skb will be retried with this driver next time, and the same result will ensue. Removing this check will catch these driver bugs instead of hiding the problem. I am keeping this change to readability section since : a. it is confusing to check two things as it is; and b. it is difficult to keep this check in the changed 'switch' code. - Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is the work being done and easier to understand) and do_dev_requeue to dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to dev_handle_collision (handle_dev_cpu_collision is a small routine with only one caller, so there is no need to have two separate routines which also results in getting rid of two macros, etc. - Removed an XXX comment as it should never fail (I suspect this was related to batch skb WIP, Jamal ?). Converted some functions to original coding style of having the return values and the function name on same line, eg prio2list. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-25 02:56:09 +00:00
*/
bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev, struct netdev_queue *txq,
spinlock_t *root_lock, bool validate)
{
int ret = NETDEV_TX_BUSY;
bool again = false;
/* And release qdisc */
if (root_lock)
spin_unlock(root_lock);
/* Note that we validate skb (GSO, checksum, ...) outside of locks */
if (validate)
skb = validate_xmit_skb_list(skb, dev, &again);
#ifdef CONFIG_XFRM_OFFLOAD
if (unlikely(again)) {
if (root_lock)
spin_lock(root_lock);
dev_requeue_skb(skb, q);
return false;
}
#endif
if (likely(skb)) {
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
skb = dev_hard_start_xmit(skb, dev, txq, &ret);
else
qdisc_maybe_clear_missed(q, txq);
HARD_TX_UNLOCK(dev, txq);
} else {
if (root_lock)
spin_lock(root_lock);
return true;
}
if (root_lock)
spin_lock(root_lock);
if (!dev_xmit_complete(ret)) {
[NET]: qdisc_restart - readability changes plus one bug fix. New changes : - Incorporated Peter Waskiewicz's comments. - Re-added back one warning message (on driver returning wrong value). Previous changes : - Converted to use switch/case code which looks neater. - "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless check should be removed, since driver will return NETDEV_TX_LOCKED only if lockless is true and driver has to do the locking. In the original code as well as the latest code, this code can result in a bug where if LLTX is not set for a driver (lockless == 0) but the driver is written wrongly to do a trylock (despite LLTX being set), the driver returns LOCKED. But since lockless is zero, the packet is requeue'd instead of calling collision code which will issue warning and free up the skb. Instead this skb will be retried with this driver next time, and the same result will ensue. Removing this check will catch these driver bugs instead of hiding the problem. I am keeping this change to readability section since : a. it is confusing to check two things as it is; and b. it is difficult to keep this check in the changed 'switch' code. - Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is the work being done and easier to understand) and do_dev_requeue to dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to dev_handle_collision (handle_dev_cpu_collision is a small routine with only one caller, so there is no need to have two separate routines which also results in getting rid of two macros, etc. - Removed an XXX comment as it should never fail (I suspect this was related to batch skb WIP, Jamal ?). Converted some functions to original coding style of having the return values and the function name on same line, eg prio2list. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-25 02:56:09 +00:00
/* Driver returned NETDEV_TX_BUSY - requeue skb */
if (unlikely(ret != NETDEV_TX_BUSY))
net_warn_ratelimited("BUG %s code %d qlen %d\n",
dev->name, ret, q->q.qlen);
[NET]: qdisc_restart - readability changes plus one bug fix. New changes : - Incorporated Peter Waskiewicz's comments. - Re-added back one warning message (on driver returning wrong value). Previous changes : - Converted to use switch/case code which looks neater. - "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless check should be removed, since driver will return NETDEV_TX_LOCKED only if lockless is true and driver has to do the locking. In the original code as well as the latest code, this code can result in a bug where if LLTX is not set for a driver (lockless == 0) but the driver is written wrongly to do a trylock (despite LLTX being set), the driver returns LOCKED. But since lockless is zero, the packet is requeue'd instead of calling collision code which will issue warning and free up the skb. Instead this skb will be retried with this driver next time, and the same result will ensue. Removing this check will catch these driver bugs instead of hiding the problem. I am keeping this change to readability section since : a. it is confusing to check two things as it is; and b. it is difficult to keep this check in the changed 'switch' code. - Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is the work being done and easier to understand) and do_dev_requeue to dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to dev_handle_collision (handle_dev_cpu_collision is a small routine with only one caller, so there is no need to have two separate routines which also results in getting rid of two macros, etc. - Removed an XXX comment as it should never fail (I suspect this was related to batch skb WIP, Jamal ?). Converted some functions to original coding style of having the return values and the function name on same line, eg prio2list. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-25 02:56:09 +00:00
dev_requeue_skb(skb, q);
return false;
[NET]: qdisc_restart - readability changes plus one bug fix. New changes : - Incorporated Peter Waskiewicz's comments. - Re-added back one warning message (on driver returning wrong value). Previous changes : - Converted to use switch/case code which looks neater. - "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless check should be removed, since driver will return NETDEV_TX_LOCKED only if lockless is true and driver has to do the locking. In the original code as well as the latest code, this code can result in a bug where if LLTX is not set for a driver (lockless == 0) but the driver is written wrongly to do a trylock (despite LLTX being set), the driver returns LOCKED. But since lockless is zero, the packet is requeue'd instead of calling collision code which will issue warning and free up the skb. Instead this skb will be retried with this driver next time, and the same result will ensue. Removing this check will catch these driver bugs instead of hiding the problem. I am keeping this change to readability section since : a. it is confusing to check two things as it is; and b. it is difficult to keep this check in the changed 'switch' code. - Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is the work being done and easier to understand) and do_dev_requeue to dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to dev_handle_collision (handle_dev_cpu_collision is a small routine with only one caller, so there is no need to have two separate routines which also results in getting rid of two macros, etc. - Removed an XXX comment as it should never fail (I suspect this was related to batch skb WIP, Jamal ?). Converted some functions to original coding style of having the return values and the function name on same line, eg prio2list. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-25 02:56:09 +00:00
}
return true;
}
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
/*
* NOTE: Called under qdisc_lock(q) with locally disabled BH.
*
* running seqcount guarantees only one CPU can process
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
* this qdisc at a time. qdisc_lock(q) serializes queue accesses for
* this queue.
*
* netif_tx_lock serializes accesses to device driver.
*
* qdisc_lock(q) and netif_tx_lock are mutually exclusive,
* if one is grabbed, another must be free.
*
* Note, that this procedure can be called by a watchdog timer
*
* Returns to the caller:
* 0 - queue is empty or throttled.
* >0 - queue is not empty.
*
*/
static inline bool qdisc_restart(struct Qdisc *q, int *packets)
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
{
spinlock_t *root_lock = NULL;
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
struct netdev_queue *txq;
struct net_device *dev;
struct sk_buff *skb;
bool validate;
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
/* Dequeue packet */
net_sched: restore qdisc quota fairness limits after bulk dequeue Restore the quota fairness between qdisc's, that we broke with commit 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"). Before that commit, the quota in __qdisc_run() were in packets as dequeue_skb() would only dequeue a single packet, that assumption broke with bulk dequeue. We choose not to account for the number of packets inside the TSO/GSO packets (accessable via "skb_gso_segs"). As the previous fairness also had this "defect". Thus, GSO/TSO packets counts as a single packet. Further more, we choose to slack on accuracy, by allowing a bulk dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only limited by the BQL bytelimit. This is done because BQL prefers to get its full budget for appropriate feedback from TX completion. In future, we might consider reworking this further and, if it allows, switch to a time-based model, as suggested by Eric. Right now, we only restore old semantics. Joint work with Eric, Hannes, Daniel and Jesper. Hannes wrote the first patch in cooperation with Daniel and Jesper. Eric rewrote the patch. Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 10:18:10 +00:00
skb = dequeue_skb(q, &validate, packets);
if (unlikely(!skb))
return false;
if (!(q->flags & TCQ_F_NOLOCK))
root_lock = qdisc_lock(q);
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
dev = qdisc_dev(q);
txq = skb_get_tx_queue(dev, skb);
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
return sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
net: Avoid enqueuing skb for default qdiscs dev_queue_xmit enqueue's a skb and calls qdisc_run which dequeue's the skb and xmits it. In most cases, the skb that is enqueue'd is the same one that is dequeue'd (unless the queue gets stopped or multiple cpu's write to the same queue and ends in a race with qdisc_run). For default qdiscs, we can remove the redundant enqueue/dequeue and simply xmit the skb since the default qdisc is work-conserving. The patch uses a new flag - TCQ_F_CAN_BYPASS to identify the default fast queue. The controversial part of the patch is incrementing qlen when a skb is requeued - this is to avoid checks like the second line below: + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && >> !q->gso_skb && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { Results of a 2 hour testing for multiple netperf sessions (1, 2, 4, 8, 12 sessions on a 4 cpu system-X). The BW numbers are aggregate Mb/s across iterations tested with this version on System-X boxes with Chelsio 10gbps cards: ---------------------------------- Size | ORG BW NEW BW | ---------------------------------- 128K | 156964 159381 | 256K | 158650 162042 | ---------------------------------- Changes from ver1: 1. Move sch_direct_xmit declaration from sch_generic.h to pkt_sched.h 2. Update qdisc basic statistics for direct xmit path. 3. Set qlen to zero in qdisc_reset. 4. Changed some function names to more meaningful ones. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-06 01:44:21 +00:00
}
void __qdisc_run(struct Qdisc *q)
{
int quota = READ_ONCE(dev_tx_weight);
net_sched: restore qdisc quota fairness limits after bulk dequeue Restore the quota fairness between qdisc's, that we broke with commit 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"). Before that commit, the quota in __qdisc_run() were in packets as dequeue_skb() would only dequeue a single packet, that assumption broke with bulk dequeue. We choose not to account for the number of packets inside the TSO/GSO packets (accessable via "skb_gso_segs"). As the previous fairness also had this "defect". Thus, GSO/TSO packets counts as a single packet. Further more, we choose to slack on accuracy, by allowing a bulk dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only limited by the BQL bytelimit. This is done because BQL prefers to get its full budget for appropriate feedback from TX completion. In future, we might consider reworking this further and, if it allows, switch to a time-based model, as suggested by Eric. Right now, we only restore old semantics. Joint work with Eric, Hannes, Daniel and Jesper. Hannes wrote the first patch in cooperation with Daniel and Jesper. Eric rewrote the patch. Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 10:18:10 +00:00
int packets;
net_sched: restore qdisc quota fairness limits after bulk dequeue Restore the quota fairness between qdisc's, that we broke with commit 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"). Before that commit, the quota in __qdisc_run() were in packets as dequeue_skb() would only dequeue a single packet, that assumption broke with bulk dequeue. We choose not to account for the number of packets inside the TSO/GSO packets (accessable via "skb_gso_segs"). As the previous fairness also had this "defect". Thus, GSO/TSO packets counts as a single packet. Further more, we choose to slack on accuracy, by allowing a bulk dequeue try_bulk_dequeue_skb() to exceed the "packets" limit, only limited by the BQL bytelimit. This is done because BQL prefers to get its full budget for appropriate feedback from TX completion. In future, we might consider reworking this further and, if it allows, switch to a time-based model, as suggested by Eric. Right now, we only restore old semantics. Joint work with Eric, Hannes, Daniel and Jesper. Hannes wrote the first patch in cooperation with Daniel and Jesper. Eric rewrote the patch. Fixes: 5772e9a346 ("qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE") Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-09 10:18:10 +00:00
while (qdisc_restart(q, &packets)) {
quota -= packets;
net_sched: remove need_resched() from qdisc_run() The introduction of this schedule point was done in commit 2ba2506ca7ca ("[NET]: Add preemption point in qdisc_run") at a time the loop was not bounded. Then later in commit d5b8aa1d246f ("net_sched: fix dequeuer fairness") we added a limit on the number of packets. Now is the time to remove the schedule point, since the default limit of 64 packets matches the number of packets a typical NAPI poll can process in a row. This solves a latency problem for most TCP receivers under moderate load : 1) host receives a packet. NET_RX_SOFTIRQ is raised by NIC hard IRQ handler 2) __do_softirq() does its first loop, handling NET_RX_SOFTIRQ and calling the driver napi->loop() function 3) TCP stores the skb in socket receive queue: 4) TCP calls sk->sk_data_ready() and wakeups a user thread waiting for EPOLLIN (as a result, need_resched() might now be true) 5) TCP cooks an ACK and sends it. 6) qdisc_run() processes one packet from qdisc, and sees need_resched(), this raises NET_TX_SOFTIRQ (even if there are no more packets in the qdisc) Then we go back to the __do_softirq() in 2), and we see that new softirqs were raised. Since need_resched() is true, we end up waking ksoftirqd in this path : if (pending) { if (time_before(jiffies, end) && !need_resched() && --max_restart) goto restart; wakeup_softirqd(); } So we have many wakeups of ksoftirqd kernel threads, and more calls to qdisc_run() with associated lock overhead. Note that another way to solve the issue would be to change TCP to first send the ACK packet, then signal the EPOLLIN, but this changes P99 latencies, as sending the ACK packet can add a long delay. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-01 21:02:36 +00:00
if (quota <= 0) {
net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK flag set, but queue discipline by-pass does not work for lockless qdisc because skb is always enqueued to qdisc even when the qdisc is empty, see __dev_xmit_skb(). This patch calls sch_direct_xmit() to transmit the skb directly to the driver for empty lockless qdisc, which aviod enqueuing and dequeuing operation. As qdisc->empty is not reliable to indicate a empty qdisc because there is a time window between enqueuing and setting qdisc->empty. So we use the MISSED state added in commit a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc"), which indicate there is lock contention, suggesting that it is better not to do the qdisc bypass in order to avoid packet out of order problem. In order to make MISSED state reliable to indicate a empty qdisc, we need to ensure that testing and clearing of MISSED state is within the protection of qdisc->seqlock, only setting MISSED state can be done without the protection of qdisc->seqlock. A MISSED state testing is added without the protection of qdisc->seqlock to aviod doing unnecessary spin_trylock() for contention case. As the enqueuing is not within the protection of qdisc->seqlock, there is still a potential data race as mentioned by Jakub [1]: thread1 thread2 thread3 qdisc_run_begin() # true qdisc_run_begin(q) set(MISSED) pfifo_fast_dequeue clear(MISSED) # recheck the queue qdisc_run_end() enqueue skb1 qdisc empty # true qdisc_run_begin() # true sch_direct_xmit() # skb2 qdisc_run_begin() set(MISSED) When above happens, skb1 enqueued by thread2 is transmited after skb2 is transmited by thread3 because MISSED state setting and enqueuing is not under the qdisc->seqlock. If qdisc bypass is disabled, skb1 has better chance to be transmited quicker than skb2. This patch does not take care of the above data race, because we view this as similar as below: Even at the same time CPU1 and CPU2 write the skb to two socket which both heading to the same qdisc, there is no guarantee that which skb will hit the qdisc first, because there is a lot of factor like interrupt/softirq/cache miss/scheduling afffecting that. There are below cases that need special handling: 1. When MISSED state is cleared before another round of dequeuing in pfifo_fast_dequeue(), and __qdisc_run() might not be able to dequeue all skb in one round and call __netif_schedule(), which might result in a non-empty qdisc without MISSED set. In order to avoid this, the MISSED state is set for lockless qdisc and __netif_schedule() will be called at the end of qdisc_run_end. 2. The MISSED state also need to be set for lockless qdisc instead of calling __netif_schedule() directly when requeuing a skb for a similar reason. 3. For netdev queue stopped case, the MISSED case need clearing while the netdev queue is stopped, otherwise there may be unnecessary __netif_schedule() calling. So a new DRAINING state is added to indicate this case, which also indicate a non-empty qdisc. 4. As there is already netif_xmit_frozen_or_stopped() checking in dequeue_skb() and sch_direct_xmit(), which are both within the protection of qdisc->seqlock, but the same checking in __dev_xmit_skb() is without the protection, which might cause empty indication of a lockless qdisc to be not reliable. So remove the checking in __dev_xmit_skb(), and the checking in the protection of qdisc->seqlock seems enough to avoid the cpu consumption problem for netdev queue stopped case. 1. https://lkml.org/lkml/2021/5/29/215 Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 06:49:56 +00:00
if (q->flags & TCQ_F_NOLOCK)
set_bit(__QDISC_STATE_MISSED, &q->state);
else
__netif_schedule(q);
break;
}
}
}
unsigned long dev_trans_start(struct net_device *dev)
{
unsigned long res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start);
unsigned long val;
unsigned int i;
for (i = 1; i < dev->num_tx_queues; i++) {
val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start);
if (val && time_after(val, res))
res = val;
}
return res;
}
EXPORT_SYMBOL(dev_trans_start);
static void netif_freeze_queues(struct net_device *dev)
{
unsigned int i;
int cpu;
cpu = smp_processor_id();
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
/* We are the only thread of execution doing a
* freeze, but we have to grab the _xmit_lock in
* order to synchronize with threads which are in
* the ->hard_start_xmit() handler and already
* checked the frozen bit.
*/
__netif_tx_lock(txq, cpu);
set_bit(__QUEUE_STATE_FROZEN, &txq->state);
__netif_tx_unlock(txq);
}
}
void netif_tx_lock(struct net_device *dev)
{
spin_lock(&dev->tx_global_lock);
netif_freeze_queues(dev);
}
EXPORT_SYMBOL(netif_tx_lock);
static void netif_unfreeze_queues(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq = netdev_get_tx_queue(dev, i);
/* No need to grab the _xmit_lock here. If the
* queue is not stopped for another reason, we
* force a schedule.
*/
clear_bit(__QUEUE_STATE_FROZEN, &txq->state);
netif_schedule_queue(txq);
}
}
void netif_tx_unlock(struct net_device *dev)
{
netif_unfreeze_queues(dev);
spin_unlock(&dev->tx_global_lock);
}
EXPORT_SYMBOL(netif_tx_unlock);
static void dev_watchdog(struct timer_list *t)
{
struct net_device *dev = from_timer(dev, t, watchdog_timer);
bool release = true;
spin_lock(&dev->tx_global_lock);
if (!qdisc_tx_is_noop(dev)) {
if (netif_device_present(dev) &&
netif_running(dev) &&
netif_carrier_ok(dev)) {
unsigned int timedout_ms = 0;
unsigned int i;
unsigned long trans_start;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq;
txq = netdev_get_tx_queue(dev, i);
trans_start = READ_ONCE(txq->trans_start);
if (netif_xmit_stopped(txq) &&
time_after(jiffies, (trans_start +
dev->watchdog_timeo))) {
timedout_ms = jiffies_to_msecs(jiffies - trans_start);
atomic_long_inc(&txq->trans_timeout);
break;
}
}
if (unlikely(timedout_ms)) {
trace_net_dev_xmit_timeout(dev, i);
WARN_ONCE(1, "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out %u ms\n",
dev->name, netdev_drivername(dev), i, timedout_ms);
netif_freeze_queues(dev);
netdev: pass the stuck queue to the timeout handler This allows incrementing the correct timeout statistic without any mess. Down the road, devices can learn to reset just the specific queue. The patch was generated with the following script: use strict; use warnings; our $^I = '.bak'; my @work = ( ["arch/m68k/emu/nfeth.c", "nfeth_tx_timeout"], ["arch/um/drivers/net_kern.c", "uml_net_tx_timeout"], ["arch/um/drivers/vector_kern.c", "vector_net_tx_timeout"], ["arch/xtensa/platforms/iss/network.c", "iss_net_tx_timeout"], ["drivers/char/pcmcia/synclink_cs.c", "hdlcdev_tx_timeout"], ["drivers/infiniband/ulp/ipoib/ipoib_main.c", "ipoib_timeout"], ["drivers/infiniband/ulp/ipoib/ipoib_main.c", "ipoib_timeout"], ["drivers/message/fusion/mptlan.c", "mpt_lan_tx_timeout"], ["drivers/misc/sgi-xp/xpnet.c", "xpnet_dev_tx_timeout"], ["drivers/net/appletalk/cops.c", "cops_timeout"], ["drivers/net/arcnet/arcdevice.h", "arcnet_timeout"], ["drivers/net/arcnet/arcnet.c", "arcnet_timeout"], ["drivers/net/arcnet/com20020.c", "arcnet_timeout"], ["drivers/net/ethernet/3com/3c509.c", "el3_tx_timeout"], ["drivers/net/ethernet/3com/3c515.c", "corkscrew_timeout"], ["drivers/net/ethernet/3com/3c574_cs.c", "el3_tx_timeout"], ["drivers/net/ethernet/3com/3c589_cs.c", "el3_tx_timeout"], ["drivers/net/ethernet/3com/3c59x.c", "vortex_tx_timeout"], ["drivers/net/ethernet/3com/3c59x.c", "vortex_tx_timeout"], ["drivers/net/ethernet/3com/typhoon.c", "typhoon_tx_timeout"], ["drivers/net/ethernet/8390/8390.h", "ei_tx_timeout"], ["drivers/net/ethernet/8390/8390.h", "eip_tx_timeout"], ["drivers/net/ethernet/8390/8390.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/8390p.c", "eip_tx_timeout"], ["drivers/net/ethernet/8390/ax88796.c", "ax_ei_tx_timeout"], ["drivers/net/ethernet/8390/axnet_cs.c", "axnet_tx_timeout"], ["drivers/net/ethernet/8390/etherh.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/hydra.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/mac8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/mcf8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/lib8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/8390/ne2k-pci.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/pcnet_cs.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/smc-ultra.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/wd.c", "ei_tx_timeout"], ["drivers/net/ethernet/8390/zorro8390.c", "__ei_tx_timeout"], ["drivers/net/ethernet/adaptec/starfire.c", "tx_timeout"], ["drivers/net/ethernet/agere/et131x.c", "et131x_tx_timeout"], ["drivers/net/ethernet/allwinner/sun4i-emac.c", "emac_timeout"], ["drivers/net/ethernet/alteon/acenic.c", "ace_watchdog"], ["drivers/net/ethernet/amazon/ena/ena_netdev.c", "ena_tx_timeout"], ["drivers/net/ethernet/amd/7990.h", "lance_tx_timeout"], ["drivers/net/ethernet/amd/7990.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/a2065.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/am79c961a.c", "am79c961_timeout"], ["drivers/net/ethernet/amd/amd8111e.c", "amd8111e_tx_timeout"], ["drivers/net/ethernet/amd/ariadne.c", "ariadne_tx_timeout"], ["drivers/net/ethernet/amd/atarilance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/au1000_eth.c", "au1000_tx_timeout"], ["drivers/net/ethernet/amd/declance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/lance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/mvme147.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/ni65.c", "ni65_timeout"], ["drivers/net/ethernet/amd/nmclan_cs.c", "mace_tx_timeout"], ["drivers/net/ethernet/amd/pcnet32.c", "pcnet32_tx_timeout"], ["drivers/net/ethernet/amd/sunlance.c", "lance_tx_timeout"], ["drivers/net/ethernet/amd/xgbe/xgbe-drv.c", "xgbe_tx_timeout"], ["drivers/net/ethernet/apm/xgene-v2/main.c", "xge_timeout"], ["drivers/net/ethernet/apm/xgene/xgene_enet_main.c", "xgene_enet_timeout"], ["drivers/net/ethernet/apple/macmace.c", "mace_tx_timeout"], ["drivers/net/ethernet/atheros/ag71xx.c", "ag71xx_tx_timeout"], ["drivers/net/ethernet/atheros/alx/main.c", "alx_tx_timeout"], ["drivers/net/ethernet/atheros/atl1c/atl1c_main.c", "atl1c_tx_timeout"], ["drivers/net/ethernet/atheros/atl1e/atl1e_main.c", "atl1e_tx_timeout"], ["drivers/net/ethernet/atheros/atlx/atl.c", "atlx_tx_timeout"], ["drivers/net/ethernet/atheros/atlx/atl1.c", "atlx_tx_timeout"], ["drivers/net/ethernet/atheros/atlx/atl2.c", "atl2_tx_timeout"], ["drivers/net/ethernet/broadcom/b44.c", "b44_tx_timeout"], ["drivers/net/ethernet/broadcom/bcmsysport.c", "bcm_sysport_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2.c", "bnx2_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h", "bnx2x_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c", "bnx2x_tx_timeout"], ["drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c", "bnx2x_tx_timeout"], ["drivers/net/ethernet/broadcom/bnxt/bnxt.c", "bnxt_tx_timeout"], ["drivers/net/ethernet/broadcom/genet/bcmgenet.c", "bcmgenet_timeout"], ["drivers/net/ethernet/broadcom/sb1250-mac.c", "sbmac_tx_timeout"], ["drivers/net/ethernet/broadcom/tg3.c", "tg3_tx_timeout"], ["drivers/net/ethernet/calxeda/xgmac.c", "xgmac_tx_timeout"], ["drivers/net/ethernet/cavium/liquidio/lio_main.c", "liquidio_tx_timeout"], ["drivers/net/ethernet/cavium/liquidio/lio_vf_main.c", "liquidio_tx_timeout"], ["drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c", "lio_vf_rep_tx_timeout"], ["drivers/net/ethernet/cavium/thunder/nicvf_main.c", "nicvf_tx_timeout"], ["drivers/net/ethernet/cirrus/cs89x0.c", "net_timeout"], ["drivers/net/ethernet/cisco/enic/enic_main.c", "enic_tx_timeout"], ["drivers/net/ethernet/cisco/enic/enic_main.c", "enic_tx_timeout"], ["drivers/net/ethernet/cortina/gemini.c", "gmac_tx_timeout"], ["drivers/net/ethernet/davicom/dm9000.c", "dm9000_timeout"], ["drivers/net/ethernet/dec/tulip/de2104x.c", "de_tx_timeout"], ["drivers/net/ethernet/dec/tulip/tulip_core.c", "tulip_tx_timeout"], ["drivers/net/ethernet/dec/tulip/winbond-840.c", "tx_timeout"], ["drivers/net/ethernet/dlink/dl2k.c", "rio_tx_timeout"], ["drivers/net/ethernet/dlink/sundance.c", "tx_timeout"], ["drivers/net/ethernet/emulex/benet/be_main.c", "be_tx_timeout"], ["drivers/net/ethernet/ethoc.c", "ethoc_tx_timeout"], ["drivers/net/ethernet/faraday/ftgmac100.c", "ftgmac100_tx_timeout"], ["drivers/net/ethernet/fealnx.c", "fealnx_tx_timeout"], ["drivers/net/ethernet/freescale/dpaa/dpaa_eth.c", "dpaa_tx_timeout"], ["drivers/net/ethernet/freescale/fec_main.c", "fec_timeout"], ["drivers/net/ethernet/freescale/fec_mpc52xx.c", "mpc52xx_fec_tx_timeout"], ["drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c", "fs_timeout"], ["drivers/net/ethernet/freescale/gianfar.c", "gfar_timeout"], ["drivers/net/ethernet/freescale/ucc_geth.c", "ucc_geth_timeout"], ["drivers/net/ethernet/fujitsu/fmvj18x_cs.c", "fjn_tx_timeout"], ["drivers/net/ethernet/google/gve/gve_main.c", "gve_tx_timeout"], ["drivers/net/ethernet/hisilicon/hip04_eth.c", "hip04_timeout"], ["drivers/net/ethernet/hisilicon/hix5hd2_gmac.c", "hix5hd2_net_timeout"], ["drivers/net/ethernet/hisilicon/hns/hns_enet.c", "hns_nic_net_timeout"], ["drivers/net/ethernet/hisilicon/hns3/hns3_enet.c", "hns3_nic_net_timeout"], ["drivers/net/ethernet/huawei/hinic/hinic_main.c", "hinic_tx_timeout"], ["drivers/net/ethernet/i825xx/82596.c", "i596_tx_timeout"], ["drivers/net/ethernet/i825xx/ether1.c", "ether1_timeout"], ["drivers/net/ethernet/i825xx/lib82596.c", "i596_tx_timeout"], ["drivers/net/ethernet/i825xx/sun3_82586.c", "sun3_82586_timeout"], ["drivers/net/ethernet/ibm/ehea/ehea_main.c", "ehea_tx_watchdog"], ["drivers/net/ethernet/ibm/emac/core.c", "emac_tx_timeout"], ["drivers/net/ethernet/ibm/emac/core.c", "emac_tx_timeout"], ["drivers/net/ethernet/ibm/ibmvnic.c", "ibmvnic_tx_timeout"], ["drivers/net/ethernet/intel/e100.c", "e100_tx_timeout"], ["drivers/net/ethernet/intel/e1000/e1000_main.c", "e1000_tx_timeout"], ["drivers/net/ethernet/intel/e1000e/netdev.c", "e1000_tx_timeout"], ["drivers/net/ethernet/intel/fm10k/fm10k_netdev.c", "fm10k_tx_timeout"], ["drivers/net/ethernet/intel/i40e/i40e_main.c", "i40e_tx_timeout"], ["drivers/net/ethernet/intel/iavf/iavf_main.c", "iavf_tx_timeout"], ["drivers/net/ethernet/intel/ice/ice_main.c", "ice_tx_timeout"], ["drivers/net/ethernet/intel/ice/ice_main.c", "ice_tx_timeout"], ["drivers/net/ethernet/intel/igb/igb_main.c", "igb_tx_timeout"], ["drivers/net/ethernet/intel/igbvf/netdev.c", "igbvf_tx_timeout"], ["drivers/net/ethernet/intel/ixgb/ixgb_main.c", "ixgb_tx_timeout"], ["drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c", "adapter->netdev->netdev_ops->ndo_tx_timeout(adapter->netdev);"], ["drivers/net/ethernet/intel/ixgbe/ixgbe_main.c", "ixgbe_tx_timeout"], ["drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c", "ixgbevf_tx_timeout"], ["drivers/net/ethernet/jme.c", "jme_tx_timeout"], ["drivers/net/ethernet/korina.c", "korina_tx_timeout"], ["drivers/net/ethernet/lantiq_etop.c", "ltq_etop_tx_timeout"], ["drivers/net/ethernet/marvell/mv643xx_eth.c", "mv643xx_eth_tx_timeout"], ["drivers/net/ethernet/marvell/pxa168_eth.c", "pxa168_eth_tx_timeout"], ["drivers/net/ethernet/marvell/skge.c", "skge_tx_timeout"], ["drivers/net/ethernet/marvell/sky2.c", "sky2_tx_timeout"], ["drivers/net/ethernet/marvell/sky2.c", "sky2_tx_timeout"], ["drivers/net/ethernet/mediatek/mtk_eth_soc.c", "mtk_tx_timeout"], ["drivers/net/ethernet/mellanox/mlx4/en_netdev.c", "mlx4_en_tx_timeout"], ["drivers/net/ethernet/mellanox/mlx4/en_netdev.c", "mlx4_en_tx_timeout"], ["drivers/net/ethernet/mellanox/mlx5/core/en_main.c", "mlx5e_tx_timeout"], ["drivers/net/ethernet/micrel/ks8842.c", "ks8842_tx_timeout"], ["drivers/net/ethernet/micrel/ksz884x.c", "netdev_tx_timeout"], ["drivers/net/ethernet/microchip/enc28j60.c", "enc28j60_tx_timeout"], ["drivers/net/ethernet/microchip/encx24j600.c", "encx24j600_tx_timeout"], ["drivers/net/ethernet/natsemi/sonic.h", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/sonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/jazzsonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/macsonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/natsemi/natsemi.c", "ns_tx_timeout"], ["drivers/net/ethernet/natsemi/ns83820.c", "ns83820_tx_timeout"], ["drivers/net/ethernet/natsemi/xtsonic.c", "sonic_tx_timeout"], ["drivers/net/ethernet/neterion/s2io.h", "s2io_tx_watchdog"], ["drivers/net/ethernet/neterion/s2io.c", "s2io_tx_watchdog"], ["drivers/net/ethernet/neterion/vxge/vxge-main.c", "vxge_tx_watchdog"], ["drivers/net/ethernet/netronome/nfp/nfp_net_common.c", "nfp_net_tx_timeout"], ["drivers/net/ethernet/nvidia/forcedeth.c", "nv_tx_timeout"], ["drivers/net/ethernet/nvidia/forcedeth.c", "nv_tx_timeout"], ["drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c", "pch_gbe_tx_timeout"], ["drivers/net/ethernet/packetengines/hamachi.c", "hamachi_tx_timeout"], ["drivers/net/ethernet/packetengines/yellowfin.c", "yellowfin_tx_timeout"], ["drivers/net/ethernet/pensando/ionic/ionic_lif.c", "ionic_tx_timeout"], ["drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c", "netxen_tx_timeout"], ["drivers/net/ethernet/qlogic/qla3xxx.c", "ql3xxx_tx_timeout"], ["drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c", "qlcnic_tx_timeout"], ["drivers/net/ethernet/qualcomm/emac/emac.c", "emac_tx_timeout"], ["drivers/net/ethernet/qualcomm/qca_spi.c", "qcaspi_netdev_tx_timeout"], ["drivers/net/ethernet/qualcomm/qca_uart.c", "qcauart_netdev_tx_timeout"], ["drivers/net/ethernet/rdc/r6040.c", "r6040_tx_timeout"], ["drivers/net/ethernet/realtek/8139cp.c", "cp_tx_timeout"], ["drivers/net/ethernet/realtek/8139too.c", "rtl8139_tx_timeout"], ["drivers/net/ethernet/realtek/atp.c", "tx_timeout"], ["drivers/net/ethernet/realtek/r8169_main.c", "rtl8169_tx_timeout"], ["drivers/net/ethernet/renesas/ravb_main.c", "ravb_tx_timeout"], ["drivers/net/ethernet/renesas/sh_eth.c", "sh_eth_tx_timeout"], ["drivers/net/ethernet/renesas/sh_eth.c", "sh_eth_tx_timeout"], ["drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c", "sxgbe_tx_timeout"], ["drivers/net/ethernet/seeq/ether3.c", "ether3_timeout"], ["drivers/net/ethernet/seeq/sgiseeq.c", "timeout"], ["drivers/net/ethernet/sfc/efx.c", "efx_watchdog"], ["drivers/net/ethernet/sfc/falcon/efx.c", "ef4_watchdog"], ["drivers/net/ethernet/sgi/ioc3-eth.c", "ioc3_timeout"], ["drivers/net/ethernet/sgi/meth.c", "meth_tx_timeout"], ["drivers/net/ethernet/silan/sc92031.c", "sc92031_tx_timeout"], ["drivers/net/ethernet/sis/sis190.c", "sis190_tx_timeout"], ["drivers/net/ethernet/sis/sis900.c", "sis900_tx_timeout"], ["drivers/net/ethernet/smsc/epic100.c", "epic_tx_timeout"], ["drivers/net/ethernet/smsc/smc911x.c", "smc911x_timeout"], ["drivers/net/ethernet/smsc/smc9194.c", "smc_timeout"], ["drivers/net/ethernet/smsc/smc91c92_cs.c", "smc_tx_timeout"], ["drivers/net/ethernet/smsc/smc91x.c", "smc_timeout"], ["drivers/net/ethernet/stmicro/stmmac/stmmac_main.c", "stmmac_tx_timeout"], ["drivers/net/ethernet/sun/cassini.c", "cas_tx_timeout"], ["drivers/net/ethernet/sun/ldmvsw.c", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/sun/niu.c", "niu_tx_timeout"], ["drivers/net/ethernet/sun/sunbmac.c", "bigmac_tx_timeout"], ["drivers/net/ethernet/sun/sungem.c", "gem_tx_timeout"], ["drivers/net/ethernet/sun/sunhme.c", "happy_meal_tx_timeout"], ["drivers/net/ethernet/sun/sunqe.c", "qe_tx_timeout"], ["drivers/net/ethernet/sun/sunvnet.c", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/sun/sunvnet_common.c", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/sun/sunvnet_common.h", "sunvnet_tx_timeout_common"], ["drivers/net/ethernet/synopsys/dwc-xlgmac-net.c", "xlgmac_tx_timeout"], ["drivers/net/ethernet/ti/cpmac.c", "cpmac_tx_timeout"], ["drivers/net/ethernet/ti/cpsw.c", "cpsw_ndo_tx_timeout"], ["drivers/net/ethernet/ti/cpsw_priv.c", "cpsw_ndo_tx_timeout"], ["drivers/net/ethernet/ti/cpsw_priv.h", "cpsw_ndo_tx_timeout"], ["drivers/net/ethernet/ti/davinci_emac.c", "emac_dev_tx_timeout"], ["drivers/net/ethernet/ti/netcp_core.c", "netcp_ndo_tx_timeout"], ["drivers/net/ethernet/ti/tlan.c", "tlan_tx_timeout"], ["drivers/net/ethernet/toshiba/ps3_gelic_net.h", "gelic_net_tx_timeout"], ["drivers/net/ethernet/toshiba/ps3_gelic_net.c", "gelic_net_tx_timeout"], ["drivers/net/ethernet/toshiba/ps3_gelic_wireless.c", "gelic_net_tx_timeout"], ["drivers/net/ethernet/toshiba/spider_net.c", "spider_net_tx_timeout"], ["drivers/net/ethernet/toshiba/tc35815.c", "tc35815_tx_timeout"], ["drivers/net/ethernet/via/via-rhine.c", "rhine_tx_timeout"], ["drivers/net/ethernet/wiznet/w5100.c", "w5100_tx_timeout"], ["drivers/net/ethernet/wiznet/w5300.c", "w5300_tx_timeout"], ["drivers/net/ethernet/xilinx/xilinx_emaclite.c", "xemaclite_tx_timeout"], ["drivers/net/ethernet/xircom/xirc2ps_cs.c", "xirc_tx_timeout"], ["drivers/net/fjes/fjes_main.c", "fjes_tx_retry"], ["drivers/net/slip/slip.c", "sl_tx_timeout"], ["include/linux/usb/usbnet.h", "usbnet_tx_timeout"], ["drivers/net/usb/aqc111.c", "usbnet_tx_timeout"], ["drivers/net/usb/asix_devices.c", "usbnet_tx_timeout"], ["drivers/net/usb/asix_devices.c", "usbnet_tx_timeout"], ["drivers/net/usb/asix_devices.c", "usbnet_tx_timeout"], ["drivers/net/usb/ax88172a.c", "usbnet_tx_timeout"], ["drivers/net/usb/ax88179_178a.c", "usbnet_tx_timeout"], ["drivers/net/usb/catc.c", "catc_tx_timeout"], ["drivers/net/usb/cdc_mbim.c", "usbnet_tx_timeout"], ["drivers/net/usb/cdc_ncm.c", "usbnet_tx_timeout"], ["drivers/net/usb/dm9601.c", "usbnet_tx_timeout"], ["drivers/net/usb/hso.c", "hso_net_tx_timeout"], ["drivers/net/usb/int51x1.c", "usbnet_tx_timeout"], ["drivers/net/usb/ipheth.c", "ipheth_tx_timeout"], ["drivers/net/usb/kaweth.c", "kaweth_tx_timeout"], ["drivers/net/usb/lan78xx.c", "lan78xx_tx_timeout"], ["drivers/net/usb/mcs7830.c", "usbnet_tx_timeout"], ["drivers/net/usb/pegasus.c", "pegasus_tx_timeout"], ["drivers/net/usb/qmi_wwan.c", "usbnet_tx_timeout"], ["drivers/net/usb/r8152.c", "rtl8152_tx_timeout"], ["drivers/net/usb/rndis_host.c", "usbnet_tx_timeout"], ["drivers/net/usb/rtl8150.c", "rtl8150_tx_timeout"], ["drivers/net/usb/sierra_net.c", "usbnet_tx_timeout"], ["drivers/net/usb/smsc75xx.c", "usbnet_tx_timeout"], ["drivers/net/usb/smsc95xx.c", "usbnet_tx_timeout"], ["drivers/net/usb/sr9700.c", "usbnet_tx_timeout"], ["drivers/net/usb/sr9800.c", "usbnet_tx_timeout"], ["drivers/net/usb/usbnet.c", "usbnet_tx_timeout"], ["drivers/net/vmxnet3/vmxnet3_drv.c", "vmxnet3_tx_timeout"], ["drivers/net/wan/cosa.c", "cosa_net_timeout"], ["drivers/net/wan/farsync.c", "fst_tx_timeout"], ["drivers/net/wan/fsl_ucc_hdlc.c", "uhdlc_tx_timeout"], ["drivers/net/wan/lmc/lmc_main.c", "lmc_driver_timeout"], ["drivers/net/wan/x25_asy.c", "x25_asy_timeout"], ["drivers/net/wimax/i2400m/netdev.c", "i2400m_tx_timeout"], ["drivers/net/wireless/intel/ipw2x00/ipw2100.c", "ipw2100_tx_timeout"], ["drivers/net/wireless/intersil/hostap/hostap_main.c", "prism2_tx_timeout"], ["drivers/net/wireless/intersil/hostap/hostap_main.c", "prism2_tx_timeout"], ["drivers/net/wireless/intersil/hostap/hostap_main.c", "prism2_tx_timeout"], ["drivers/net/wireless/intersil/orinoco/main.c", "orinoco_tx_timeout"], ["drivers/net/wireless/intersil/orinoco/orinoco_usb.c", "orinoco_tx_timeout"], ["drivers/net/wireless/intersil/orinoco/orinoco.h", "orinoco_tx_timeout"], ["drivers/net/wireless/intersil/prism54/islpci_dev.c", "islpci_eth_tx_timeout"], ["drivers/net/wireless/intersil/prism54/islpci_eth.c", "islpci_eth_tx_timeout"], ["drivers/net/wireless/intersil/prism54/islpci_eth.h", "islpci_eth_tx_timeout"], ["drivers/net/wireless/marvell/mwifiex/main.c", "mwifiex_tx_timeout"], ["drivers/net/wireless/quantenna/qtnfmac/core.c", "qtnf_netdev_tx_timeout"], ["drivers/net/wireless/quantenna/qtnfmac/core.h", "qtnf_netdev_tx_timeout"], ["drivers/net/wireless/rndis_wlan.c", "usbnet_tx_timeout"], ["drivers/net/wireless/wl3501_cs.c", "wl3501_tx_timeout"], ["drivers/net/wireless/zydas/zd1201.c", "zd1201_tx_timeout"], ["drivers/s390/net/qeth_core.h", "qeth_tx_timeout"], ["drivers/s390/net/qeth_core_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l2_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l2_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l3_main.c", "qeth_tx_timeout"], ["drivers/s390/net/qeth_l3_main.c", "qeth_tx_timeout"], ["drivers/staging/ks7010/ks_wlan_net.c", "ks_wlan_tx_timeout"], ["drivers/staging/qlge/qlge_main.c", "qlge_tx_timeout"], ["drivers/staging/rtl8192e/rtl8192e/rtl_core.c", "_rtl92e_tx_timeout"], ["drivers/staging/rtl8192u/r8192U_core.c", "tx_timeout"], ["drivers/staging/unisys/visornic/visornic_main.c", "visornic_xmit_timeout"], ["drivers/staging/wlan-ng/p80211netdev.c", "p80211knetdev_tx_timeout"], ["drivers/tty/n_gsm.c", "gsm_mux_net_tx_timeout"], ["drivers/tty/synclink.c", "hdlcdev_tx_timeout"], ["drivers/tty/synclink_gt.c", "hdlcdev_tx_timeout"], ["drivers/tty/synclinkmp.c", "hdlcdev_tx_timeout"], ["net/atm/lec.c", "lec_tx_timeout"], ["net/bluetooth/bnep/netdev.c", "bnep_net_timeout"] ); for my $p (@work) { my @pair = @$p; my $file = $pair[0]; my $func = $pair[1]; print STDERR $file , ": ", $func,"\n"; our @ARGV = ($file); while (<ARGV>) { if (m/($func\s*\(struct\s+net_device\s+\*[A-Za-z_]?[A-Za-z-0-9_]*)(\))/) { print STDERR "found $1+$2 in $file\n"; } if (s/($func\s*\(struct\s+net_device\s+\*[A-Za-z_]?[A-Za-z-0-9_]*)(\))/$1, unsigned int txqueue$2/) { print STDERR "$func found in $file\n"; } print; } } where the list of files and functions is simply from: git grep ndo_tx_timeout, with manual addition of headers in the rare cases where the function is from a header, then manually changing the few places which actually call ndo_tx_timeout. Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Heiner Kallweit <hkallweit1@gmail.com> Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com> Acked-by: Shannon Nelson <snelson@pensando.io> Reviewed-by: Martin Habets <mhabets@solarflare.com> changes from v9: fixup a forward declaration changes from v9: more leftovers from v3 change changes from v8: fix up a missing direct call to timeout rebased on net-next changes from v7: fixup leftovers from v3 change changes from v6: fix typo in rtl driver changes from v5: add missing files (allow any net device argument name) changes from v4: add a missing driver header changes from v3: change queue # to unsigned Changes from v2: added headers Changes from v1: Fix errors found by kbuild: generalize the pattern a bit, to pick up a couple of instances missed by the previous version. Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-10 14:23:51 +00:00
dev->netdev_ops->ndo_tx_timeout(dev, i);
netif_unfreeze_queues(dev);
}
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies +
dev->watchdog_timeo)))
release = false;
}
}
spin_unlock(&dev->tx_global_lock);
if (release)
netdev_put(dev, &dev->watchdog_dev_tracker);
}
void __netdev_watchdog_up(struct net_device *dev)
{
if (dev->netdev_ops->ndo_tx_timeout) {
if (dev->watchdog_timeo <= 0)
dev->watchdog_timeo = 5*HZ;
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies + dev->watchdog_timeo)))
netdev_hold(dev, &dev->watchdog_dev_tracker,
GFP_ATOMIC);
}
}
EXPORT_SYMBOL_GPL(__netdev_watchdog_up);
static void dev_watchdog_up(struct net_device *dev)
{
__netdev_watchdog_up(dev);
}
static void dev_watchdog_down(struct net_device *dev)
{
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 19:20:56 +00:00
netif_tx_lock_bh(dev);
if (del_timer(&dev->watchdog_timer))
netdev_put(dev, &dev->watchdog_dev_tracker);
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 19:20:56 +00:00
netif_tx_unlock_bh(dev);
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
/**
* netif_carrier_on - set carrier
* @dev: network device
*
* Device has detected acquisition of carrier.
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
*/
void netif_carrier_on(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
atomic_inc(&dev->carrier_up_count);
linkwatch_fire_event(dev);
if (netif_running(dev))
__netdev_watchdog_up(dev);
}
}
EXPORT_SYMBOL(netif_carrier_on);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-03 23:41:36 +00:00
/**
* netif_carrier_off - clear carrier
* @dev: network device
*
* Device has detected loss of carrier.
*/
void netif_carrier_off(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
atomic_inc(&dev->carrier_down_count);
linkwatch_fire_event(dev);
}
}
EXPORT_SYMBOL(netif_carrier_off);
/**
* netif_carrier_event - report carrier state event
* @dev: network device
*
* Device has detected a carrier event but the carrier state wasn't changed.
* Use in drivers when querying carrier state asynchronously, to avoid missing
* events (link flaps) if link recovers before it's queried.
*/
void netif_carrier_event(struct net_device *dev)
{
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
atomic_inc(&dev->carrier_up_count);
atomic_inc(&dev->carrier_down_count);
linkwatch_fire_event(dev);
}
EXPORT_SYMBOL_GPL(netif_carrier_event);
/* "NOOP" scheduler: the best scheduler, recommended for all interfaces
under all circumstances. It is difficult to invent anything faster or
cheaper.
*/
static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
struct sk_buff **to_free)
{
__qdisc_drop(skb, to_free);
return NET_XMIT_CN;
}
static struct sk_buff *noop_dequeue(struct Qdisc *qdisc)
{
return NULL;
}
struct Qdisc_ops noop_qdisc_ops __read_mostly = {
.id = "noop",
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.peek = noop_dequeue,
.owner = THIS_MODULE,
};
static struct netdev_queue noop_netdev_queue = {
RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc),
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
RCU_POINTER_INITIALIZER(qdisc_sleeping, &noop_qdisc),
};
struct Qdisc noop_qdisc = {
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.flags = TCQ_F_BUILTIN,
.ops = &noop_qdisc_ops,
.q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
.dev_queue = &noop_netdev_queue,
.busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
.gso_skb = {
.next = (struct sk_buff *)&noop_qdisc.gso_skb,
.prev = (struct sk_buff *)&noop_qdisc.gso_skb,
.qlen = 0,
.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock),
},
.skb_bad_txq = {
.next = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
.prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq,
.qlen = 0,
.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock),
},
};
EXPORT_SYMBOL(noop_qdisc);
static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
/* register_qdisc() assigns a default of noop_enqueue if unset,
* but __dev_queue_xmit() treats noqueue only as such
* if this is NULL - so clear it here. */
qdisc->enqueue = NULL;
return 0;
}
struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
.id = "noqueue",
.priv_size = 0,
.init = noqueue_init,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.peek = noop_dequeue,
.owner = THIS_MODULE,
};
static const u8 prio2band[TC_PRIO_MAX + 1] = {
1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
};
/* 3-band FIFO queue: old style, but should be a bit faster than
generic prio+fifo combination.
*/
#define PFIFO_FAST_BANDS 3
/*
* Private data for a pfifo_fast scheduler containing:
* - rings for priority bands
*/
struct pfifo_fast_priv {
struct skb_array q[PFIFO_FAST_BANDS];
};
static inline struct skb_array *band2list(struct pfifo_fast_priv *priv,
int band)
{
return &priv->q[band];
}
static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
struct sk_buff **to_free)
{
int band = prio2band[skb->priority & TC_PRIO_MAX];
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct skb_array *q = band2list(priv, band);
net: sched: fix uses after free syzbot reported one use-after-free in pfifo_fast_enqueue() [1] Issue here is that we can not reuse skb after a successful skb_array_produce() since another cpu might have consumed it already. I believe a similar problem exists in try_bulk_dequeue_skb_slow() in case we put an skb into qdisc_enqueue_skb_bad_txq() for lockless qdisc. [1] BUG: KASAN: use-after-free in qdisc_pkt_len include/net/sch_generic.h:610 [inline] BUG: KASAN: use-after-free in qdisc_qstats_cpu_backlog_inc include/net/sch_generic.h:712 [inline] BUG: KASAN: use-after-free in pfifo_fast_enqueue+0x4bc/0x5e0 net/sched/sch_generic.c:639 Read of size 4 at addr ffff8801cede37e8 by task syzkaller717588/5543 CPU: 1 PID: 5543 Comm: syzkaller717588 Not tainted 4.16.0-rc4+ #265 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x194/0x24d lib/dump_stack.c:53 print_address_description+0x73/0x250 mm/kasan/report.c:256 kasan_report_error mm/kasan/report.c:354 [inline] kasan_report+0x23c/0x360 mm/kasan/report.c:412 __asan_report_load4_noabort+0x14/0x20 mm/kasan/report.c:432 qdisc_pkt_len include/net/sch_generic.h:610 [inline] qdisc_qstats_cpu_backlog_inc include/net/sch_generic.h:712 [inline] pfifo_fast_enqueue+0x4bc/0x5e0 net/sched/sch_generic.c:639 __dev_xmit_skb net/core/dev.c:3216 [inline] Fixes: c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot+ed43b6903ab968b16f54@syzkaller.appspotmail.com Cc: John Fastabend <john.fastabend@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-15 01:53:00 +00:00
unsigned int pkt_len = qdisc_pkt_len(skb);
int err;
err = skb_array_produce(q, skb);
net/sched: pfifo_fast: fix wrong dereference in pfifo_fast_enqueue Now that 'TCQ_F_CPUSTATS' bit can be cleared, depending on the value of 'TCQ_F_NOLOCK' bit in the parent qdisc, we can't assume anymore that per-cpu counters are there in the error path of skb_array_produce(). Otherwise, the following splat can be seen: Unable to handle kernel paging request at virtual address 0000600dea430008 Mem abort info: ESR = 0x96000005 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000005 CM = 0, WnR = 0 user pgtable: 64k pages, 48-bit VAs, pgdp = 000000007b97530e [0000600dea430008] pgd=0000000000000000, pud=0000000000000000 Internal error: Oops: 96000005 [#1] SMP [...] pstate: 10000005 (nzcV daif -PAN -UAO) pc : pfifo_fast_enqueue+0x524/0x6e8 lr : pfifo_fast_enqueue+0x46c/0x6e8 sp : ffff800d39376fe0 x29: ffff800d39376fe0 x28: 1ffff001a07d1e40 x27: ffff800d03e8f188 x26: ffff800d03e8f200 x25: 0000000000000062 x24: ffff800d393772f0 x23: 0000000000000000 x22: 0000000000000403 x21: ffff800cca569a00 x20: ffff800d03e8ee00 x19: ffff800cca569a10 x18: 00000000000000bf x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: ffff1001a726edd0 x13: 1fffe4000276a9a4 x12: 0000000000000000 x11: dfff200000000000 x10: ffff800d03e8f1a0 x9 : 0000000000000003 x8 : 0000000000000000 x7 : 00000000f1f1f1f1 x6 : ffff1001a726edea x5 : ffff800cca56a53c x4 : 1ffff001bf9a8003 x3 : 1ffff001bf9a8003 x2 : 1ffff001a07d1dcb x1 : 0000600dea430000 x0 : 0000600dea430008 Process ping (pid: 6067, stack limit = 0x00000000dc0aa557) Call trace: pfifo_fast_enqueue+0x524/0x6e8 htb_enqueue+0x660/0x10e0 [sch_htb] __dev_queue_xmit+0x123c/0x2de0 dev_queue_xmit+0x24/0x30 ip_finish_output2+0xc48/0x1720 ip_finish_output+0x548/0x9d8 ip_output+0x334/0x788 ip_local_out+0x90/0x138 ip_send_skb+0x44/0x1d0 ip_push_pending_frames+0x5c/0x78 raw_sendmsg+0xed8/0x28d0 inet_sendmsg+0xc4/0x5c0 sock_sendmsg+0xac/0x108 __sys_sendto+0x1ac/0x2a0 __arm64_sys_sendto+0xc4/0x138 el0_svc_handler+0x13c/0x298 el0_svc+0x8/0xc Code: f9402e80 d538d081 91002000 8b010000 (885f7c03) Fix this by testing the value of 'TCQ_F_CPUSTATS' bit in 'qdisc->flags', before dereferencing 'qdisc->cpu_qstats'. Fixes: 8a53e616de29 ("net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too") CC: Paolo Abeni <pabeni@redhat.com> CC: Stefano Brivio <sbrivio@redhat.com> Reported-by: Li Shuang <shuali@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-27 21:18:53 +00:00
if (unlikely(err)) {
if (qdisc_is_percpu_stats(qdisc))
return qdisc_drop_cpu(skb, qdisc, to_free);
else
return qdisc_drop(skb, qdisc, to_free);
}
qdisc_update_stats_at_enqueue(qdisc, pkt_len);
return NET_XMIT_SUCCESS;
}
static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
{
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct sk_buff *skb = NULL;
net: sched: fix packet stuck problem for lockless qdisc Lockless qdisc has below concurrent problem: cpu0 cpu1 . . q->enqueue . . . qdisc_run_begin() . . . dequeue_skb() . . . sch_direct_xmit() . . . . q->enqueue . qdisc_run_begin() . return and do nothing . . qdisc_run_end() . cpu1 enqueue a skb without calling __qdisc_run() because cpu0 has not released the lock yet and spin_trylock() return false for cpu1 in qdisc_run_begin(), and cpu0 do not see the skb enqueued by cpu1 when calling dequeue_skb() because cpu1 may enqueue the skb after cpu0 calling dequeue_skb() and before cpu0 calling qdisc_run_end(). Lockless qdisc has below another concurrent problem when tx_action is involved: cpu0(serving tx_action) cpu1 cpu2 . . . . q->enqueue . . qdisc_run_begin() . . dequeue_skb() . . . q->enqueue . . . . sch_direct_xmit() . . . qdisc_run_begin() . . return and do nothing . . . clear __QDISC_STATE_SCHED . . qdisc_run_begin() . . return and do nothing . . . . . . qdisc_run_end() . This patch fixes the above data race by: 1. If the first spin_trylock() return false and STATE_MISSED is not set, set STATE_MISSED and retry another spin_trylock() in case other CPU may not see STATE_MISSED after it releases the lock. 2. reschedule if STATE_MISSED is set after the lock is released at the end of qdisc_run_end(). For tx_action case, STATE_MISSED is also set when cpu1 is at the end if qdisc_run_end(), so tx_action will be rescheduled again to dequeue the skb enqueued by cpu2. Clear STATE_MISSED before retrying a dequeuing when dequeuing returns NULL in order to reduce the overhead of the second spin_trylock() and __netif_schedule() calling. Also clear the STATE_MISSED before calling __netif_schedule() at the end of qdisc_run_end() to avoid doing another round of dequeuing in the pfifo_fast_dequeue(). The performance impact of this patch, tested using pktgen and dummy netdev with pfifo_fast qdisc attached: threads without+this_patch with+this_patch delta 1 2.61Mpps 2.60Mpps -0.3% 2 3.97Mpps 3.82Mpps -3.7% 4 5.62Mpps 5.59Mpps -0.5% 8 2.78Mpps 2.77Mpps -0.3% 16 2.22Mpps 2.22Mpps -0.0% Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Juergen Gross <jgross@suse.com> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-14 03:16:59 +00:00
bool need_retry = true;
int band;
net: sched: fix packet stuck problem for lockless qdisc Lockless qdisc has below concurrent problem: cpu0 cpu1 . . q->enqueue . . . qdisc_run_begin() . . . dequeue_skb() . . . sch_direct_xmit() . . . . q->enqueue . qdisc_run_begin() . return and do nothing . . qdisc_run_end() . cpu1 enqueue a skb without calling __qdisc_run() because cpu0 has not released the lock yet and spin_trylock() return false for cpu1 in qdisc_run_begin(), and cpu0 do not see the skb enqueued by cpu1 when calling dequeue_skb() because cpu1 may enqueue the skb after cpu0 calling dequeue_skb() and before cpu0 calling qdisc_run_end(). Lockless qdisc has below another concurrent problem when tx_action is involved: cpu0(serving tx_action) cpu1 cpu2 . . . . q->enqueue . . qdisc_run_begin() . . dequeue_skb() . . . q->enqueue . . . . sch_direct_xmit() . . . qdisc_run_begin() . . return and do nothing . . . clear __QDISC_STATE_SCHED . . qdisc_run_begin() . . return and do nothing . . . . . . qdisc_run_end() . This patch fixes the above data race by: 1. If the first spin_trylock() return false and STATE_MISSED is not set, set STATE_MISSED and retry another spin_trylock() in case other CPU may not see STATE_MISSED after it releases the lock. 2. reschedule if STATE_MISSED is set after the lock is released at the end of qdisc_run_end(). For tx_action case, STATE_MISSED is also set when cpu1 is at the end if qdisc_run_end(), so tx_action will be rescheduled again to dequeue the skb enqueued by cpu2. Clear STATE_MISSED before retrying a dequeuing when dequeuing returns NULL in order to reduce the overhead of the second spin_trylock() and __netif_schedule() calling. Also clear the STATE_MISSED before calling __netif_schedule() at the end of qdisc_run_end() to avoid doing another round of dequeuing in the pfifo_fast_dequeue(). The performance impact of this patch, tested using pktgen and dummy netdev with pfifo_fast qdisc attached: threads without+this_patch with+this_patch delta 1 2.61Mpps 2.60Mpps -0.3% 2 3.97Mpps 3.82Mpps -3.7% 4 5.62Mpps 5.59Mpps -0.5% 8 2.78Mpps 2.77Mpps -0.3% 16 2.22Mpps 2.22Mpps -0.0% Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Juergen Gross <jgross@suse.com> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-14 03:16:59 +00:00
retry:
for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
struct skb_array *q = band2list(priv, band);
if (__skb_array_empty(q))
continue;
skb = __skb_array_consume(q);
}
if (likely(skb)) {
qdisc_update_stats_at_dequeue(qdisc, skb);
net: sched: fix packet stuck problem for lockless qdisc Lockless qdisc has below concurrent problem: cpu0 cpu1 . . q->enqueue . . . qdisc_run_begin() . . . dequeue_skb() . . . sch_direct_xmit() . . . . q->enqueue . qdisc_run_begin() . return and do nothing . . qdisc_run_end() . cpu1 enqueue a skb without calling __qdisc_run() because cpu0 has not released the lock yet and spin_trylock() return false for cpu1 in qdisc_run_begin(), and cpu0 do not see the skb enqueued by cpu1 when calling dequeue_skb() because cpu1 may enqueue the skb after cpu0 calling dequeue_skb() and before cpu0 calling qdisc_run_end(). Lockless qdisc has below another concurrent problem when tx_action is involved: cpu0(serving tx_action) cpu1 cpu2 . . . . q->enqueue . . qdisc_run_begin() . . dequeue_skb() . . . q->enqueue . . . . sch_direct_xmit() . . . qdisc_run_begin() . . return and do nothing . . . clear __QDISC_STATE_SCHED . . qdisc_run_begin() . . return and do nothing . . . . . . qdisc_run_end() . This patch fixes the above data race by: 1. If the first spin_trylock() return false and STATE_MISSED is not set, set STATE_MISSED and retry another spin_trylock() in case other CPU may not see STATE_MISSED after it releases the lock. 2. reschedule if STATE_MISSED is set after the lock is released at the end of qdisc_run_end(). For tx_action case, STATE_MISSED is also set when cpu1 is at the end if qdisc_run_end(), so tx_action will be rescheduled again to dequeue the skb enqueued by cpu2. Clear STATE_MISSED before retrying a dequeuing when dequeuing returns NULL in order to reduce the overhead of the second spin_trylock() and __netif_schedule() calling. Also clear the STATE_MISSED before calling __netif_schedule() at the end of qdisc_run_end() to avoid doing another round of dequeuing in the pfifo_fast_dequeue(). The performance impact of this patch, tested using pktgen and dummy netdev with pfifo_fast qdisc attached: threads without+this_patch with+this_patch delta 1 2.61Mpps 2.60Mpps -0.3% 2 3.97Mpps 3.82Mpps -3.7% 4 5.62Mpps 5.59Mpps -0.5% 8 2.78Mpps 2.77Mpps -0.3% 16 2.22Mpps 2.22Mpps -0.0% Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Juergen Gross <jgross@suse.com> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-14 03:16:59 +00:00
} else if (need_retry &&
net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK flag set, but queue discipline by-pass does not work for lockless qdisc because skb is always enqueued to qdisc even when the qdisc is empty, see __dev_xmit_skb(). This patch calls sch_direct_xmit() to transmit the skb directly to the driver for empty lockless qdisc, which aviod enqueuing and dequeuing operation. As qdisc->empty is not reliable to indicate a empty qdisc because there is a time window between enqueuing and setting qdisc->empty. So we use the MISSED state added in commit a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc"), which indicate there is lock contention, suggesting that it is better not to do the qdisc bypass in order to avoid packet out of order problem. In order to make MISSED state reliable to indicate a empty qdisc, we need to ensure that testing and clearing of MISSED state is within the protection of qdisc->seqlock, only setting MISSED state can be done without the protection of qdisc->seqlock. A MISSED state testing is added without the protection of qdisc->seqlock to aviod doing unnecessary spin_trylock() for contention case. As the enqueuing is not within the protection of qdisc->seqlock, there is still a potential data race as mentioned by Jakub [1]: thread1 thread2 thread3 qdisc_run_begin() # true qdisc_run_begin(q) set(MISSED) pfifo_fast_dequeue clear(MISSED) # recheck the queue qdisc_run_end() enqueue skb1 qdisc empty # true qdisc_run_begin() # true sch_direct_xmit() # skb2 qdisc_run_begin() set(MISSED) When above happens, skb1 enqueued by thread2 is transmited after skb2 is transmited by thread3 because MISSED state setting and enqueuing is not under the qdisc->seqlock. If qdisc bypass is disabled, skb1 has better chance to be transmited quicker than skb2. This patch does not take care of the above data race, because we view this as similar as below: Even at the same time CPU1 and CPU2 write the skb to two socket which both heading to the same qdisc, there is no guarantee that which skb will hit the qdisc first, because there is a lot of factor like interrupt/softirq/cache miss/scheduling afffecting that. There are below cases that need special handling: 1. When MISSED state is cleared before another round of dequeuing in pfifo_fast_dequeue(), and __qdisc_run() might not be able to dequeue all skb in one round and call __netif_schedule(), which might result in a non-empty qdisc without MISSED set. In order to avoid this, the MISSED state is set for lockless qdisc and __netif_schedule() will be called at the end of qdisc_run_end. 2. The MISSED state also need to be set for lockless qdisc instead of calling __netif_schedule() directly when requeuing a skb for a similar reason. 3. For netdev queue stopped case, the MISSED case need clearing while the netdev queue is stopped, otherwise there may be unnecessary __netif_schedule() calling. So a new DRAINING state is added to indicate this case, which also indicate a non-empty qdisc. 4. As there is already netif_xmit_frozen_or_stopped() checking in dequeue_skb() and sch_direct_xmit(), which are both within the protection of qdisc->seqlock, but the same checking in __dev_xmit_skb() is without the protection, which might cause empty indication of a lockless qdisc to be not reliable. So remove the checking in __dev_xmit_skb(), and the checking in the protection of qdisc->seqlock seems enough to avoid the cpu consumption problem for netdev queue stopped case. 1. https://lkml.org/lkml/2021/5/29/215 Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 06:49:56 +00:00
READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) {
net: sched: fix packet stuck problem for lockless qdisc Lockless qdisc has below concurrent problem: cpu0 cpu1 . . q->enqueue . . . qdisc_run_begin() . . . dequeue_skb() . . . sch_direct_xmit() . . . . q->enqueue . qdisc_run_begin() . return and do nothing . . qdisc_run_end() . cpu1 enqueue a skb without calling __qdisc_run() because cpu0 has not released the lock yet and spin_trylock() return false for cpu1 in qdisc_run_begin(), and cpu0 do not see the skb enqueued by cpu1 when calling dequeue_skb() because cpu1 may enqueue the skb after cpu0 calling dequeue_skb() and before cpu0 calling qdisc_run_end(). Lockless qdisc has below another concurrent problem when tx_action is involved: cpu0(serving tx_action) cpu1 cpu2 . . . . q->enqueue . . qdisc_run_begin() . . dequeue_skb() . . . q->enqueue . . . . sch_direct_xmit() . . . qdisc_run_begin() . . return and do nothing . . . clear __QDISC_STATE_SCHED . . qdisc_run_begin() . . return and do nothing . . . . . . qdisc_run_end() . This patch fixes the above data race by: 1. If the first spin_trylock() return false and STATE_MISSED is not set, set STATE_MISSED and retry another spin_trylock() in case other CPU may not see STATE_MISSED after it releases the lock. 2. reschedule if STATE_MISSED is set after the lock is released at the end of qdisc_run_end(). For tx_action case, STATE_MISSED is also set when cpu1 is at the end if qdisc_run_end(), so tx_action will be rescheduled again to dequeue the skb enqueued by cpu2. Clear STATE_MISSED before retrying a dequeuing when dequeuing returns NULL in order to reduce the overhead of the second spin_trylock() and __netif_schedule() calling. Also clear the STATE_MISSED before calling __netif_schedule() at the end of qdisc_run_end() to avoid doing another round of dequeuing in the pfifo_fast_dequeue(). The performance impact of this patch, tested using pktgen and dummy netdev with pfifo_fast qdisc attached: threads without+this_patch with+this_patch delta 1 2.61Mpps 2.60Mpps -0.3% 2 3.97Mpps 3.82Mpps -3.7% 4 5.62Mpps 5.59Mpps -0.5% 8 2.78Mpps 2.77Mpps -0.3% 16 2.22Mpps 2.22Mpps -0.0% Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Juergen Gross <jgross@suse.com> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-14 03:16:59 +00:00
/* Delay clearing the STATE_MISSED here to reduce
* the overhead of the second spin_trylock() in
* qdisc_run_begin() and __netif_schedule() calling
* in qdisc_run_end().
*/
clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK flag set, but queue discipline by-pass does not work for lockless qdisc because skb is always enqueued to qdisc even when the qdisc is empty, see __dev_xmit_skb(). This patch calls sch_direct_xmit() to transmit the skb directly to the driver for empty lockless qdisc, which aviod enqueuing and dequeuing operation. As qdisc->empty is not reliable to indicate a empty qdisc because there is a time window between enqueuing and setting qdisc->empty. So we use the MISSED state added in commit a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc"), which indicate there is lock contention, suggesting that it is better not to do the qdisc bypass in order to avoid packet out of order problem. In order to make MISSED state reliable to indicate a empty qdisc, we need to ensure that testing and clearing of MISSED state is within the protection of qdisc->seqlock, only setting MISSED state can be done without the protection of qdisc->seqlock. A MISSED state testing is added without the protection of qdisc->seqlock to aviod doing unnecessary spin_trylock() for contention case. As the enqueuing is not within the protection of qdisc->seqlock, there is still a potential data race as mentioned by Jakub [1]: thread1 thread2 thread3 qdisc_run_begin() # true qdisc_run_begin(q) set(MISSED) pfifo_fast_dequeue clear(MISSED) # recheck the queue qdisc_run_end() enqueue skb1 qdisc empty # true qdisc_run_begin() # true sch_direct_xmit() # skb2 qdisc_run_begin() set(MISSED) When above happens, skb1 enqueued by thread2 is transmited after skb2 is transmited by thread3 because MISSED state setting and enqueuing is not under the qdisc->seqlock. If qdisc bypass is disabled, skb1 has better chance to be transmited quicker than skb2. This patch does not take care of the above data race, because we view this as similar as below: Even at the same time CPU1 and CPU2 write the skb to two socket which both heading to the same qdisc, there is no guarantee that which skb will hit the qdisc first, because there is a lot of factor like interrupt/softirq/cache miss/scheduling afffecting that. There are below cases that need special handling: 1. When MISSED state is cleared before another round of dequeuing in pfifo_fast_dequeue(), and __qdisc_run() might not be able to dequeue all skb in one round and call __netif_schedule(), which might result in a non-empty qdisc without MISSED set. In order to avoid this, the MISSED state is set for lockless qdisc and __netif_schedule() will be called at the end of qdisc_run_end. 2. The MISSED state also need to be set for lockless qdisc instead of calling __netif_schedule() directly when requeuing a skb for a similar reason. 3. For netdev queue stopped case, the MISSED case need clearing while the netdev queue is stopped, otherwise there may be unnecessary __netif_schedule() calling. So a new DRAINING state is added to indicate this case, which also indicate a non-empty qdisc. 4. As there is already netif_xmit_frozen_or_stopped() checking in dequeue_skb() and sch_direct_xmit(), which are both within the protection of qdisc->seqlock, but the same checking in __dev_xmit_skb() is without the protection, which might cause empty indication of a lockless qdisc to be not reliable. So remove the checking in __dev_xmit_skb(), and the checking in the protection of qdisc->seqlock seems enough to avoid the cpu consumption problem for netdev queue stopped case. 1. https://lkml.org/lkml/2021/5/29/215 Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 06:49:56 +00:00
clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
net: sched: fix packet stuck problem for lockless qdisc Lockless qdisc has below concurrent problem: cpu0 cpu1 . . q->enqueue . . . qdisc_run_begin() . . . dequeue_skb() . . . sch_direct_xmit() . . . . q->enqueue . qdisc_run_begin() . return and do nothing . . qdisc_run_end() . cpu1 enqueue a skb without calling __qdisc_run() because cpu0 has not released the lock yet and spin_trylock() return false for cpu1 in qdisc_run_begin(), and cpu0 do not see the skb enqueued by cpu1 when calling dequeue_skb() because cpu1 may enqueue the skb after cpu0 calling dequeue_skb() and before cpu0 calling qdisc_run_end(). Lockless qdisc has below another concurrent problem when tx_action is involved: cpu0(serving tx_action) cpu1 cpu2 . . . . q->enqueue . . qdisc_run_begin() . . dequeue_skb() . . . q->enqueue . . . . sch_direct_xmit() . . . qdisc_run_begin() . . return and do nothing . . . clear __QDISC_STATE_SCHED . . qdisc_run_begin() . . return and do nothing . . . . . . qdisc_run_end() . This patch fixes the above data race by: 1. If the first spin_trylock() return false and STATE_MISSED is not set, set STATE_MISSED and retry another spin_trylock() in case other CPU may not see STATE_MISSED after it releases the lock. 2. reschedule if STATE_MISSED is set after the lock is released at the end of qdisc_run_end(). For tx_action case, STATE_MISSED is also set when cpu1 is at the end if qdisc_run_end(), so tx_action will be rescheduled again to dequeue the skb enqueued by cpu2. Clear STATE_MISSED before retrying a dequeuing when dequeuing returns NULL in order to reduce the overhead of the second spin_trylock() and __netif_schedule() calling. Also clear the STATE_MISSED before calling __netif_schedule() at the end of qdisc_run_end() to avoid doing another round of dequeuing in the pfifo_fast_dequeue(). The performance impact of this patch, tested using pktgen and dummy netdev with pfifo_fast qdisc attached: threads without+this_patch with+this_patch delta 1 2.61Mpps 2.60Mpps -0.3% 2 3.97Mpps 3.82Mpps -3.7% 4 5.62Mpps 5.59Mpps -0.5% 8 2.78Mpps 2.77Mpps -0.3% 16 2.22Mpps 2.22Mpps -0.0% Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Juergen Gross <jgross@suse.com> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-14 03:16:59 +00:00
/* Make sure dequeuing happens after clearing
* STATE_MISSED.
*/
smp_mb__after_atomic();
need_retry = false;
goto retry;
}
return skb;
}
static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc)
{
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct sk_buff *skb = NULL;
int band;
for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
struct skb_array *q = band2list(priv, band);
skb = __skb_array_peek(q);
}
return skb;
}
static void pfifo_fast_reset(struct Qdisc *qdisc)
{
int i, band;
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
for (band = 0; band < PFIFO_FAST_BANDS; band++) {
struct skb_array *q = band2list(priv, band);
struct sk_buff *skb;
/* NULL ring is possible if destroy path is due to a failed
* skb_array_init() in pfifo_fast_init() case.
*/
if (!q->ring.queue)
continue;
while ((skb = __skb_array_consume(q)) != NULL)
kfree_skb(skb);
}
net/sched: pfifo_fast: fix wrong dereference when qdisc is reset Now that 'TCQ_F_CPUSTATS' bit can be cleared, depending on the value of 'TCQ_F_NOLOCK' bit in the parent qdisc, we need to be sure that per-cpu counters are present when 'reset()' is called for pfifo_fast qdiscs. Otherwise, the following script: # tc q a dev lo handle 1: root htb default 100 # tc c a dev lo parent 1: classid 1:100 htb \ > rate 95Mbit ceil 100Mbit burst 64k [...] # tc f a dev lo parent 1: protocol arp basic classid 1:100 [...] # tc q a dev lo parent 1:100 handle 100: pfifo_fast [...] # tc q d dev lo root can generate the following splat: Unable to handle kernel paging request at virtual address dfff2c01bd148000 Mem abort info: ESR = 0x96000004 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 [dfff2c01bd148000] address between user and kernel address ranges Internal error: Oops: 96000004 [#1] SMP [...] pstate: 80000005 (Nzcv daif -PAN -UAO) pc : pfifo_fast_reset+0x280/0x4d8 lr : pfifo_fast_reset+0x21c/0x4d8 sp : ffff800d09676fa0 x29: ffff800d09676fa0 x28: ffff200012ee22e4 x27: dfff200000000000 x26: 0000000000000000 x25: ffff800ca0799958 x24: ffff1001940f332b x23: 0000000000000007 x22: ffff200012ee1ab8 x21: 0000600de8a40000 x20: 0000000000000000 x19: ffff800ca0799900 x18: 0000000000000000 x17: 0000000000000002 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: ffff1001b922e6e2 x11: 1ffff001b922e6e1 x10: 0000000000000000 x9 : 1ffff001b922e6e1 x8 : dfff200000000000 x7 : 0000000000000000 x6 : 0000000000000000 x5 : 1fffe400025dc45c x4 : 1fffe400025dc357 x3 : 00000c01bd148000 x2 : 0000600de8a40000 x1 : 0000000000000007 x0 : 0000600de8a40004 Call trace: pfifo_fast_reset+0x280/0x4d8 qdisc_reset+0x6c/0x370 htb_reset+0x150/0x3b8 [sch_htb] qdisc_reset+0x6c/0x370 dev_deactivate_queue.constprop.5+0xe0/0x1a8 dev_deactivate_many+0xd8/0x908 dev_deactivate+0xe4/0x190 qdisc_graft+0x88c/0xbd0 tc_get_qdisc+0x418/0x8a8 rtnetlink_rcv_msg+0x3a8/0xa78 netlink_rcv_skb+0x18c/0x328 rtnetlink_rcv+0x28/0x38 netlink_unicast+0x3c4/0x538 netlink_sendmsg+0x538/0x9a0 sock_sendmsg+0xac/0xf8 ___sys_sendmsg+0x53c/0x658 __sys_sendmsg+0xc8/0x140 __arm64_sys_sendmsg+0x74/0xa8 el0_svc_handler+0x164/0x468 el0_svc+0x10/0x14 Code: 910012a0 92400801 d343fc03 11000c21 (38fb6863) Fix this by testing the value of 'TCQ_F_CPUSTATS' bit in 'qdisc->flags', before dereferencing 'qdisc->cpu_qstats'. Changes since v1: - coding style improvements, thanks to Stefano Brivio Fixes: 8a53e616de29 ("net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too") CC: Paolo Abeni <pabeni@redhat.com> Reported-by: Li Shuang <shuali@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Stefano Brivio <sbrivio@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-27 10:29:09 +00:00
if (qdisc_is_percpu_stats(qdisc)) {
for_each_possible_cpu(i) {
struct gnet_stats_queue *q;
net/sched: pfifo_fast: fix wrong dereference when qdisc is reset Now that 'TCQ_F_CPUSTATS' bit can be cleared, depending on the value of 'TCQ_F_NOLOCK' bit in the parent qdisc, we need to be sure that per-cpu counters are present when 'reset()' is called for pfifo_fast qdiscs. Otherwise, the following script: # tc q a dev lo handle 1: root htb default 100 # tc c a dev lo parent 1: classid 1:100 htb \ > rate 95Mbit ceil 100Mbit burst 64k [...] # tc f a dev lo parent 1: protocol arp basic classid 1:100 [...] # tc q a dev lo parent 1:100 handle 100: pfifo_fast [...] # tc q d dev lo root can generate the following splat: Unable to handle kernel paging request at virtual address dfff2c01bd148000 Mem abort info: ESR = 0x96000004 Exception class = DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 [dfff2c01bd148000] address between user and kernel address ranges Internal error: Oops: 96000004 [#1] SMP [...] pstate: 80000005 (Nzcv daif -PAN -UAO) pc : pfifo_fast_reset+0x280/0x4d8 lr : pfifo_fast_reset+0x21c/0x4d8 sp : ffff800d09676fa0 x29: ffff800d09676fa0 x28: ffff200012ee22e4 x27: dfff200000000000 x26: 0000000000000000 x25: ffff800ca0799958 x24: ffff1001940f332b x23: 0000000000000007 x22: ffff200012ee1ab8 x21: 0000600de8a40000 x20: 0000000000000000 x19: ffff800ca0799900 x18: 0000000000000000 x17: 0000000000000002 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: ffff1001b922e6e2 x11: 1ffff001b922e6e1 x10: 0000000000000000 x9 : 1ffff001b922e6e1 x8 : dfff200000000000 x7 : 0000000000000000 x6 : 0000000000000000 x5 : 1fffe400025dc45c x4 : 1fffe400025dc357 x3 : 00000c01bd148000 x2 : 0000600de8a40000 x1 : 0000000000000007 x0 : 0000600de8a40004 Call trace: pfifo_fast_reset+0x280/0x4d8 qdisc_reset+0x6c/0x370 htb_reset+0x150/0x3b8 [sch_htb] qdisc_reset+0x6c/0x370 dev_deactivate_queue.constprop.5+0xe0/0x1a8 dev_deactivate_many+0xd8/0x908 dev_deactivate+0xe4/0x190 qdisc_graft+0x88c/0xbd0 tc_get_qdisc+0x418/0x8a8 rtnetlink_rcv_msg+0x3a8/0xa78 netlink_rcv_skb+0x18c/0x328 rtnetlink_rcv+0x28/0x38 netlink_unicast+0x3c4/0x538 netlink_sendmsg+0x538/0x9a0 sock_sendmsg+0xac/0xf8 ___sys_sendmsg+0x53c/0x658 __sys_sendmsg+0xc8/0x140 __arm64_sys_sendmsg+0x74/0xa8 el0_svc_handler+0x164/0x468 el0_svc+0x10/0x14 Code: 910012a0 92400801 d343fc03 11000c21 (38fb6863) Fix this by testing the value of 'TCQ_F_CPUSTATS' bit in 'qdisc->flags', before dereferencing 'qdisc->cpu_qstats'. Changes since v1: - coding style improvements, thanks to Stefano Brivio Fixes: 8a53e616de29 ("net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too") CC: Paolo Abeni <pabeni@redhat.com> Reported-by: Li Shuang <shuali@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Stefano Brivio <sbrivio@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-08-27 10:29:09 +00:00
q = per_cpu_ptr(qdisc->cpu_qstats, i);
q->backlog = 0;
q->qlen = 0;
}
}
}
static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb)
{
struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
return skb->len;
nla_put_failure:
return -1;
}
static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len;
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
int prio;
/* guard against zero length rings */
if (!qlen)
return -EINVAL;
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
struct skb_array *q = band2list(priv, prio);
int err;
err = skb_array_init(q, qlen, GFP_KERNEL);
if (err)
return -ENOMEM;
}
/* Can by-pass the queue discipline */
qdisc->flags |= TCQ_F_CAN_BYPASS;
return 0;
}
static void pfifo_fast_destroy(struct Qdisc *sch)
{
struct pfifo_fast_priv *priv = qdisc_priv(sch);
int prio;
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
struct skb_array *q = band2list(priv, prio);
/* NULL ring is possible if destroy path is due to a failed
* skb_array_init() in pfifo_fast_init() case.
*/
if (!q->ring.queue)
continue;
/* Destroy ring but no need to kfree_skb because a call to
* pfifo_fast_reset() has already done that work.
*/
ptr_ring_cleanup(&q->ring, NULL);
}
}
static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch,
unsigned int new_len)
{
struct pfifo_fast_priv *priv = qdisc_priv(sch);
struct skb_array *bands[PFIFO_FAST_BANDS];
int prio;
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) {
struct skb_array *q = band2list(priv, prio);
bands[prio] = q;
}
return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len,
GFP_KERNEL);
}
struct Qdisc_ops pfifo_fast_ops __read_mostly = {
.id = "pfifo_fast",
.priv_size = sizeof(struct pfifo_fast_priv),
.enqueue = pfifo_fast_enqueue,
.dequeue = pfifo_fast_dequeue,
.peek = pfifo_fast_peek,
.init = pfifo_fast_init,
.destroy = pfifo_fast_destroy,
.reset = pfifo_fast_reset,
.dump = pfifo_fast_dump,
.change_tx_queue_len = pfifo_fast_change_tx_queue_len,
.owner = THIS_MODULE,
.static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS,
};
EXPORT_SYMBOL(pfifo_fast_ops);
static struct lock_class_key qdisc_tx_busylock;
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
const struct Qdisc_ops *ops,
struct netlink_ext_ack *extack)
{
struct Qdisc *sch;
unsigned int size = sizeof(*sch) + ops->priv_size;
int err = -ENOBUFS;
struct net_device *dev;
if (!dev_queue) {
NL_SET_ERR_MSG(extack, "No device queue given");
err = -EINVAL;
goto errout;
}
dev = dev_queue->dev;
sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue));
if (!sch)
goto errout;
__skb_queue_head_init(&sch->gso_skb);
__skb_queue_head_init(&sch->skb_bad_txq);
gnet_stats_basic_sync_init(&sch->bstats);
spin_lock_init(&sch->q.lock);
net: qdisc busylock needs lockdep annotations It seems we need to provide ability for stacked devices to use specific lock_class_key for sch->busylock We could instead default l2tpeth tx_queue_len to 0 (no qdisc), but a user might use a qdisc anyway. (So same fixes are probably needed on non LLTX stacked drivers) Noticed while stressing L2TPV3 setup : ====================================================== [ INFO: possible circular locking dependency detected ] 3.6.0-rc3+ #788 Not tainted ------------------------------------------------------- netperf/4660 is trying to acquire lock: (l2tpsock){+.-...}, at: [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core] but task is already holding lock: (&(&sch->busylock)->rlock){+.-...}, at: [<ffffffff81596595>] dev_queue_xmit+0xd75/0xe00 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&(&sch->busylock)->rlock){+.-...}: [<ffffffff810a5df0>] lock_acquire+0x90/0x200 [<ffffffff817499fc>] _raw_spin_lock_irqsave+0x4c/0x60 [<ffffffff81074872>] __wake_up+0x32/0x70 [<ffffffff8136d39e>] tty_wakeup+0x3e/0x80 [<ffffffff81378fb3>] pty_write+0x73/0x80 [<ffffffff8136cb4c>] tty_put_char+0x3c/0x40 [<ffffffff813722b2>] process_echoes+0x142/0x330 [<ffffffff813742ab>] n_tty_receive_buf+0x8fb/0x1230 [<ffffffff813777b2>] flush_to_ldisc+0x142/0x1c0 [<ffffffff81062818>] process_one_work+0x198/0x760 [<ffffffff81063236>] worker_thread+0x186/0x4b0 [<ffffffff810694d3>] kthread+0x93/0xa0 [<ffffffff81753e24>] kernel_thread_helper+0x4/0x10 -> #0 (l2tpsock){+.-...}: [<ffffffff810a5288>] __lock_acquire+0x1628/0x1b10 [<ffffffff810a5df0>] lock_acquire+0x90/0x200 [<ffffffff817498c1>] _raw_spin_lock+0x41/0x50 [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [<ffffffffa021a802>] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth] [<ffffffff815952b2>] dev_hard_start_xmit+0x502/0xa70 [<ffffffff815b63ce>] sch_direct_xmit+0xfe/0x290 [<ffffffff81595a05>] dev_queue_xmit+0x1e5/0xe00 [<ffffffff815d9d60>] ip_finish_output+0x3d0/0x890 [<ffffffff815db019>] ip_output+0x59/0xf0 [<ffffffff815da36d>] ip_local_out+0x2d/0xa0 [<ffffffff815da5a3>] ip_queue_xmit+0x1c3/0x680 [<ffffffff815f4192>] tcp_transmit_skb+0x402/0xa60 [<ffffffff815f4a94>] tcp_write_xmit+0x1f4/0xa30 [<ffffffff815f5300>] tcp_push_one+0x30/0x40 [<ffffffff815e6672>] tcp_sendmsg+0xe82/0x1040 [<ffffffff81614495>] inet_sendmsg+0x125/0x230 [<ffffffff81576cdc>] sock_sendmsg+0xdc/0xf0 [<ffffffff81579ece>] sys_sendto+0xfe/0x130 [<ffffffff81752c92>] system_call_fastpath+0x16/0x1b Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&(&sch->busylock)->rlock); lock(l2tpsock); lock(&(&sch->busylock)->rlock); lock(l2tpsock); *** DEADLOCK *** 5 locks held by netperf/4660: #0: (sk_lock-AF_INET){+.+.+.}, at: [<ffffffff815e581c>] tcp_sendmsg+0x2c/0x1040 #1: (rcu_read_lock){.+.+..}, at: [<ffffffff815da3e0>] ip_queue_xmit+0x0/0x680 #2: (rcu_read_lock_bh){.+....}, at: [<ffffffff815d9ac5>] ip_finish_output+0x135/0x890 #3: (rcu_read_lock_bh){.+....}, at: [<ffffffff81595820>] dev_queue_xmit+0x0/0xe00 #4: (&(&sch->busylock)->rlock){+.-...}, at: [<ffffffff81596595>] dev_queue_xmit+0xd75/0xe00 stack backtrace: Pid: 4660, comm: netperf Not tainted 3.6.0-rc3+ #788 Call Trace: [<ffffffff8173dbf8>] print_circular_bug+0x1fb/0x20c [<ffffffff810a5288>] __lock_acquire+0x1628/0x1b10 [<ffffffff810a334b>] ? check_usage+0x9b/0x4d0 [<ffffffff810a3f44>] ? __lock_acquire+0x2e4/0x1b10 [<ffffffff810a5df0>] lock_acquire+0x90/0x200 [<ffffffffa0208db2>] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [<ffffffff817498c1>] _raw_spin_lock+0x41/0x50 [<ffffffffa0208db2>] ? l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [<ffffffffa0208db2>] l2tp_xmit_skb+0x172/0xa50 [l2tp_core] [<ffffffffa021a802>] l2tp_eth_dev_xmit+0x32/0x60 [l2tp_eth] [<ffffffff815952b2>] dev_hard_start_xmit+0x502/0xa70 [<ffffffff81594e0e>] ? dev_hard_start_xmit+0x5e/0xa70 [<ffffffff81595961>] ? dev_queue_xmit+0x141/0xe00 [<ffffffff815b63ce>] sch_direct_xmit+0xfe/0x290 [<ffffffff81595a05>] dev_queue_xmit+0x1e5/0xe00 [<ffffffff81595820>] ? dev_hard_start_xmit+0xa70/0xa70 [<ffffffff815d9d60>] ip_finish_output+0x3d0/0x890 [<ffffffff815d9ac5>] ? ip_finish_output+0x135/0x890 [<ffffffff815db019>] ip_output+0x59/0xf0 [<ffffffff815da36d>] ip_local_out+0x2d/0xa0 [<ffffffff815da5a3>] ip_queue_xmit+0x1c3/0x680 [<ffffffff815da3e0>] ? ip_local_out+0xa0/0xa0 [<ffffffff815f4192>] tcp_transmit_skb+0x402/0xa60 [<ffffffff815fa25e>] ? tcp_md5_do_lookup+0x18e/0x1a0 [<ffffffff815f4a94>] tcp_write_xmit+0x1f4/0xa30 [<ffffffff815f5300>] tcp_push_one+0x30/0x40 [<ffffffff815e6672>] tcp_sendmsg+0xe82/0x1040 [<ffffffff81614495>] inet_sendmsg+0x125/0x230 [<ffffffff81614370>] ? inet_create+0x6b0/0x6b0 [<ffffffff8157e6e2>] ? sock_update_classid+0xc2/0x3b0 [<ffffffff8157e750>] ? sock_update_classid+0x130/0x3b0 [<ffffffff81576cdc>] sock_sendmsg+0xdc/0xf0 [<ffffffff81162579>] ? fget_light+0x3f9/0x4f0 [<ffffffff81579ece>] sys_sendto+0xfe/0x130 [<ffffffff810a69ad>] ? trace_hardirqs_on+0xd/0x10 [<ffffffff8174a0b0>] ? _raw_spin_unlock_irq+0x30/0x50 [<ffffffff810757e3>] ? finish_task_switch+0x83/0xf0 [<ffffffff810757a6>] ? finish_task_switch+0x46/0xf0 [<ffffffff81752cb7>] ? sysret_check+0x1b/0x56 [<ffffffff81752c92>] system_call_fastpath+0x16/0x1b Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-09-05 01:02:56 +00:00
if (ops->static_flags & TCQ_F_CPUSTATS) {
sch->cpu_bstats =
netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync);
if (!sch->cpu_bstats)
goto errout1;
sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue);
if (!sch->cpu_qstats) {
free_percpu(sch->cpu_bstats);
goto errout1;
}
}
spin_lock_init(&sch->busylock);
lockdep_set_class(&sch->busylock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
/* seqlock has the same scope of busylock, for NOLOCK qdisc */
spin_lock_init(&sch->seqlock);
lockdep_set_class(&sch->seqlock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
sch->ops = ops;
sch->flags = ops->static_flags;
sch->enqueue = ops->enqueue;
sch->dequeue = ops->dequeue;
sch->dev_queue = dev_queue;
netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL);
refcount_set(&sch->refcnt, 1);
return sch;
errout1:
kfree(sch);
errout:
return ERR_PTR(err);
}
struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
const struct Qdisc_ops *ops,
unsigned int parentid,
struct netlink_ext_ack *extack)
{
struct Qdisc *sch;
if (!try_module_get(ops->owner)) {
NL_SET_ERR_MSG(extack, "Failed to increase module reference counter");
return NULL;
}
sch = qdisc_alloc(dev_queue, ops, extack);
if (IS_ERR(sch)) {
module_put(ops->owner);
return NULL;
}
sch->parent = parentid;
if (!ops->init || ops->init(sch, NULL, extack) == 0) {
trace_qdisc_create(ops, dev_queue->dev, parentid);
return sch;
}
qdisc_put(sch);
return NULL;
}
EXPORT_SYMBOL(qdisc_create_dflt);
/* Under qdisc_lock(qdisc) and BH! */
void qdisc_reset(struct Qdisc *qdisc)
{
const struct Qdisc_ops *ops = qdisc->ops;
trace_qdisc_reset(qdisc);
if (ops->reset)
ops->reset(qdisc);
__skb_queue_purge(&qdisc->gso_skb);
__skb_queue_purge(&qdisc->skb_bad_txq);
qdisc->q.qlen = 0;
qdisc->qstats.backlog = 0;
}
EXPORT_SYMBOL(qdisc_reset);
net, sched: fix panic when updating miniq {b,q}stats While working on fixing another bug, I ran into the following panic on arm64 by simply attaching clsact qdisc, adding a filter and running traffic on ingress to it: [...] [ 178.188591] Unable to handle kernel read from unreadable memory at virtual address 810fb501f000 [ 178.197314] Mem abort info: [ 178.200121] ESR = 0x96000004 [ 178.203168] Exception class = DABT (current EL), IL = 32 bits [ 178.209095] SET = 0, FnV = 0 [ 178.212157] EA = 0, S1PTW = 0 [ 178.215288] Data abort info: [ 178.218175] ISV = 0, ISS = 0x00000004 [ 178.222019] CM = 0, WnR = 0 [ 178.224997] user pgtable: 4k pages, 48-bit VAs, pgd = 0000000023cb3f33 [ 178.231531] [0000810fb501f000] *pgd=0000000000000000 [ 178.236508] Internal error: Oops: 96000004 [#1] SMP [...] [ 178.311855] CPU: 73 PID: 2497 Comm: ping Tainted: G W 4.15.0-rc7+ #5 [ 178.319413] Hardware name: FOXCONN R2-1221R-A4/C2U4N_MB, BIOS G31FB18A 03/31/2017 [ 178.326887] pstate: 60400005 (nZCv daif +PAN -UAO) [ 178.331685] pc : __netif_receive_skb_core+0x49c/0xac8 [ 178.336728] lr : __netif_receive_skb+0x28/0x78 [ 178.341161] sp : ffff00002344b750 [ 178.344465] x29: ffff00002344b750 x28: ffff810fbdfd0580 [ 178.349769] x27: 0000000000000000 x26: ffff000009378000 [...] [ 178.418715] x1 : 0000000000000054 x0 : 0000000000000000 [ 178.424020] Process ping (pid: 2497, stack limit = 0x000000009f0a3ff4) [ 178.430537] Call trace: [ 178.432976] __netif_receive_skb_core+0x49c/0xac8 [ 178.437670] __netif_receive_skb+0x28/0x78 [ 178.441757] process_backlog+0x9c/0x160 [ 178.445584] net_rx_action+0x2f8/0x3f0 [...] Reason is that sch_ingress and sch_clsact are doing mini_qdisc_pair_init() which sets up miniq pointers to cpu_{b,q}stats from the underlying qdisc. Problem is that this cannot work since they are actually set up right after the qdisc ->init() callback in qdisc_create(), so first packet going into sch_handle_ingress() tries to call mini_qdisc_bstats_cpu_update() and we therefore panic. In order to fix this, allocation of {b,q}stats needs to happen before we call into ->init(). In net-next, there's already such option through commit d59f5ffa59d8 ("net: sched: a dflt qdisc may be used with per cpu stats"). However, the bug needs to be fixed in net still for 4.15. Thus, include these bits to reduce any merge churn and reuse the static_flags field to set TCQ_F_CPUSTATS, and remove the allocation from qdisc_create() since there is no other user left. Prashant Bhole ran into the same issue but for net-next, thus adding him below as well as co-author. Same issue was also reported by Sandipan Das when using bcc. Fixes: 46209401f8f6 ("net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath") Reference: https://lists.iovisor.org/pipermail/iovisor-dev/2018-January/001190.html Reported-by: Sandipan Das <sandipan@linux.vnet.ibm.com> Co-authored-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp> Co-authored-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-15 22:12:09 +00:00
void qdisc_free(struct Qdisc *qdisc)
{
if (qdisc_is_percpu_stats(qdisc)) {
free_percpu(qdisc->cpu_bstats);
free_percpu(qdisc->cpu_qstats);
}
kfree(qdisc);
}
static void qdisc_free_cb(struct rcu_head *head)
{
struct Qdisc *q = container_of(head, struct Qdisc, rcu);
qdisc_free(q);
}
net/sched: qdisc_destroy() old ingress and clsact Qdiscs before grafting mini_Qdisc_pair::p_miniq is a double pointer to mini_Qdisc, initialized in ingress_init() to point to net_device::miniq_ingress. ingress Qdiscs access this per-net_device pointer in mini_qdisc_pair_swap(). Similar for clsact Qdiscs and miniq_egress. Unfortunately, after introducing RTNL-unlocked RTM_{NEW,DEL,GET}TFILTER requests (thanks Hillf Danton for the hint), when replacing ingress or clsact Qdiscs, for example, the old Qdisc ("@old") could access the same miniq_{in,e}gress pointer(s) concurrently with the new Qdisc ("@new"), causing race conditions [1] including a use-after-free bug in mini_qdisc_pair_swap() reported by syzbot: BUG: KASAN: slab-use-after-free in mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 Write of size 8 at addr ffff888045b31308 by task syz-executor690/14901 ... Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:319 print_report mm/kasan/report.c:430 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:536 mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 tcf_chain_head_change_item net/sched/cls_api.c:495 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:509 tcf_chain_tp_insert net/sched/cls_api.c:1826 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1875 [inline] tc_new_tfilter+0x1de6/0x2290 net/sched/cls_api.c:2266 ... @old and @new should not affect each other. In other words, @old should never modify miniq_{in,e}gress after @new, and @new should not update @old's RCU state. Fixing without changing sch_api.c turned out to be difficult (please refer to Closes: for discussions). Instead, make sure @new's first call always happen after @old's last call (in {ingress,clsact}_destroy()) has finished: In qdisc_graft(), return -EBUSY if @old has any ongoing filter requests, and call qdisc_destroy() for @old before grafting @new. Introduce qdisc_refcount_dec_if_one() as the counterpart of qdisc_refcount_inc_nz() used for filter requests. Introduce a non-static version of qdisc_destroy() that does a TCQ_F_BUILTIN check, just like qdisc_put() etc. Depends on patch "net/sched: Refactor qdisc_graft() for ingress and clsact Qdiscs". [1] To illustrate, the syzkaller reproducer adds ingress Qdiscs under TC_H_ROOT (no longer possible after commit c7cfbd115001 ("net/sched: sch_ingress: Only create under TC_H_INGRESS")) on eth0 that has 8 transmission queues: Thread 1 creates ingress Qdisc A (containing mini Qdisc a1 and a2), then adds a flower filter X to A. Thread 2 creates another ingress Qdisc B (containing mini Qdisc b1 and b2) to replace A, then adds a flower filter Y to B. Thread 1 A's refcnt Thread 2 RTM_NEWQDISC (A, RTNL-locked) qdisc_create(A) 1 qdisc_graft(A) 9 RTM_NEWTFILTER (X, RTNL-unlocked) __tcf_qdisc_find(A) 10 tcf_chain0_head_change(A) mini_qdisc_pair_swap(A) (1st) | | RTM_NEWQDISC (B, RTNL-locked) RCU sync 2 qdisc_graft(B) | 1 notify_and_destroy(A) | tcf_block_release(A) 0 RTM_NEWTFILTER (Y, RTNL-unlocked) qdisc_destroy(A) tcf_chain0_head_change(B) tcf_chain0_head_change_cb_del(A) mini_qdisc_pair_swap(B) (2nd) mini_qdisc_pair_swap(A) (3rd) | ... ... Here, B calls mini_qdisc_pair_swap(), pointing eth0->miniq_ingress to its mini Qdisc, b1. Then, A calls mini_qdisc_pair_swap() again during ingress_destroy(), setting eth0->miniq_ingress to NULL, so ingress packets on eth0 will not find filter Y in sch_handle_ingress(). This is just one of the possible consequences of concurrently accessing miniq_{in,e}gress pointers. Fixes: 7a096d579e8e ("net: sched: ingress: set 'unlocked' flag for Qdisc ops") Fixes: 87f373921c4e ("net: sched: ingress: set 'unlocked' flag for clsact Qdisc ops") Reported-by: syzbot+b53a9c0d1ea4ad62da8b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/0000000000006cf87705f79acf1a@google.com/ Cc: Hillf Danton <hdanton@sina.com> Cc: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-06-11 03:30:25 +00:00
static void __qdisc_destroy(struct Qdisc *qdisc)
{
const struct Qdisc_ops *ops = qdisc->ops;
#ifdef CONFIG_NET_SCHED
qdisc_hash_del(qdisc);
qdisc_put_stab(rtnl_dereference(qdisc->stab));
#endif
gen_kill_estimator(&qdisc->rate_est);
qdisc_reset(qdisc);
if (ops->destroy)
ops->destroy(qdisc);
module_put(ops->owner);
netdev_put(qdisc_dev(qdisc), &qdisc->dev_tracker);
trace_qdisc_destroy(qdisc);
call_rcu(&qdisc->rcu, qdisc_free_cb);
}
net/sched: qdisc_destroy() old ingress and clsact Qdiscs before grafting mini_Qdisc_pair::p_miniq is a double pointer to mini_Qdisc, initialized in ingress_init() to point to net_device::miniq_ingress. ingress Qdiscs access this per-net_device pointer in mini_qdisc_pair_swap(). Similar for clsact Qdiscs and miniq_egress. Unfortunately, after introducing RTNL-unlocked RTM_{NEW,DEL,GET}TFILTER requests (thanks Hillf Danton for the hint), when replacing ingress or clsact Qdiscs, for example, the old Qdisc ("@old") could access the same miniq_{in,e}gress pointer(s) concurrently with the new Qdisc ("@new"), causing race conditions [1] including a use-after-free bug in mini_qdisc_pair_swap() reported by syzbot: BUG: KASAN: slab-use-after-free in mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 Write of size 8 at addr ffff888045b31308 by task syz-executor690/14901 ... Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:319 print_report mm/kasan/report.c:430 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:536 mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 tcf_chain_head_change_item net/sched/cls_api.c:495 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:509 tcf_chain_tp_insert net/sched/cls_api.c:1826 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1875 [inline] tc_new_tfilter+0x1de6/0x2290 net/sched/cls_api.c:2266 ... @old and @new should not affect each other. In other words, @old should never modify miniq_{in,e}gress after @new, and @new should not update @old's RCU state. Fixing without changing sch_api.c turned out to be difficult (please refer to Closes: for discussions). Instead, make sure @new's first call always happen after @old's last call (in {ingress,clsact}_destroy()) has finished: In qdisc_graft(), return -EBUSY if @old has any ongoing filter requests, and call qdisc_destroy() for @old before grafting @new. Introduce qdisc_refcount_dec_if_one() as the counterpart of qdisc_refcount_inc_nz() used for filter requests. Introduce a non-static version of qdisc_destroy() that does a TCQ_F_BUILTIN check, just like qdisc_put() etc. Depends on patch "net/sched: Refactor qdisc_graft() for ingress and clsact Qdiscs". [1] To illustrate, the syzkaller reproducer adds ingress Qdiscs under TC_H_ROOT (no longer possible after commit c7cfbd115001 ("net/sched: sch_ingress: Only create under TC_H_INGRESS")) on eth0 that has 8 transmission queues: Thread 1 creates ingress Qdisc A (containing mini Qdisc a1 and a2), then adds a flower filter X to A. Thread 2 creates another ingress Qdisc B (containing mini Qdisc b1 and b2) to replace A, then adds a flower filter Y to B. Thread 1 A's refcnt Thread 2 RTM_NEWQDISC (A, RTNL-locked) qdisc_create(A) 1 qdisc_graft(A) 9 RTM_NEWTFILTER (X, RTNL-unlocked) __tcf_qdisc_find(A) 10 tcf_chain0_head_change(A) mini_qdisc_pair_swap(A) (1st) | | RTM_NEWQDISC (B, RTNL-locked) RCU sync 2 qdisc_graft(B) | 1 notify_and_destroy(A) | tcf_block_release(A) 0 RTM_NEWTFILTER (Y, RTNL-unlocked) qdisc_destroy(A) tcf_chain0_head_change(B) tcf_chain0_head_change_cb_del(A) mini_qdisc_pair_swap(B) (2nd) mini_qdisc_pair_swap(A) (3rd) | ... ... Here, B calls mini_qdisc_pair_swap(), pointing eth0->miniq_ingress to its mini Qdisc, b1. Then, A calls mini_qdisc_pair_swap() again during ingress_destroy(), setting eth0->miniq_ingress to NULL, so ingress packets on eth0 will not find filter Y in sch_handle_ingress(). This is just one of the possible consequences of concurrently accessing miniq_{in,e}gress pointers. Fixes: 7a096d579e8e ("net: sched: ingress: set 'unlocked' flag for Qdisc ops") Fixes: 87f373921c4e ("net: sched: ingress: set 'unlocked' flag for clsact Qdisc ops") Reported-by: syzbot+b53a9c0d1ea4ad62da8b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/0000000000006cf87705f79acf1a@google.com/ Cc: Hillf Danton <hdanton@sina.com> Cc: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-06-11 03:30:25 +00:00
void qdisc_destroy(struct Qdisc *qdisc)
{
if (qdisc->flags & TCQ_F_BUILTIN)
return;
__qdisc_destroy(qdisc);
}
void qdisc_put(struct Qdisc *qdisc)
{
if (!qdisc)
return;
if (qdisc->flags & TCQ_F_BUILTIN ||
!refcount_dec_and_test(&qdisc->refcnt))
return;
net/sched: qdisc_destroy() old ingress and clsact Qdiscs before grafting mini_Qdisc_pair::p_miniq is a double pointer to mini_Qdisc, initialized in ingress_init() to point to net_device::miniq_ingress. ingress Qdiscs access this per-net_device pointer in mini_qdisc_pair_swap(). Similar for clsact Qdiscs and miniq_egress. Unfortunately, after introducing RTNL-unlocked RTM_{NEW,DEL,GET}TFILTER requests (thanks Hillf Danton for the hint), when replacing ingress or clsact Qdiscs, for example, the old Qdisc ("@old") could access the same miniq_{in,e}gress pointer(s) concurrently with the new Qdisc ("@new"), causing race conditions [1] including a use-after-free bug in mini_qdisc_pair_swap() reported by syzbot: BUG: KASAN: slab-use-after-free in mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 Write of size 8 at addr ffff888045b31308 by task syz-executor690/14901 ... Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:319 print_report mm/kasan/report.c:430 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:536 mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 tcf_chain_head_change_item net/sched/cls_api.c:495 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:509 tcf_chain_tp_insert net/sched/cls_api.c:1826 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1875 [inline] tc_new_tfilter+0x1de6/0x2290 net/sched/cls_api.c:2266 ... @old and @new should not affect each other. In other words, @old should never modify miniq_{in,e}gress after @new, and @new should not update @old's RCU state. Fixing without changing sch_api.c turned out to be difficult (please refer to Closes: for discussions). Instead, make sure @new's first call always happen after @old's last call (in {ingress,clsact}_destroy()) has finished: In qdisc_graft(), return -EBUSY if @old has any ongoing filter requests, and call qdisc_destroy() for @old before grafting @new. Introduce qdisc_refcount_dec_if_one() as the counterpart of qdisc_refcount_inc_nz() used for filter requests. Introduce a non-static version of qdisc_destroy() that does a TCQ_F_BUILTIN check, just like qdisc_put() etc. Depends on patch "net/sched: Refactor qdisc_graft() for ingress and clsact Qdiscs". [1] To illustrate, the syzkaller reproducer adds ingress Qdiscs under TC_H_ROOT (no longer possible after commit c7cfbd115001 ("net/sched: sch_ingress: Only create under TC_H_INGRESS")) on eth0 that has 8 transmission queues: Thread 1 creates ingress Qdisc A (containing mini Qdisc a1 and a2), then adds a flower filter X to A. Thread 2 creates another ingress Qdisc B (containing mini Qdisc b1 and b2) to replace A, then adds a flower filter Y to B. Thread 1 A's refcnt Thread 2 RTM_NEWQDISC (A, RTNL-locked) qdisc_create(A) 1 qdisc_graft(A) 9 RTM_NEWTFILTER (X, RTNL-unlocked) __tcf_qdisc_find(A) 10 tcf_chain0_head_change(A) mini_qdisc_pair_swap(A) (1st) | | RTM_NEWQDISC (B, RTNL-locked) RCU sync 2 qdisc_graft(B) | 1 notify_and_destroy(A) | tcf_block_release(A) 0 RTM_NEWTFILTER (Y, RTNL-unlocked) qdisc_destroy(A) tcf_chain0_head_change(B) tcf_chain0_head_change_cb_del(A) mini_qdisc_pair_swap(B) (2nd) mini_qdisc_pair_swap(A) (3rd) | ... ... Here, B calls mini_qdisc_pair_swap(), pointing eth0->miniq_ingress to its mini Qdisc, b1. Then, A calls mini_qdisc_pair_swap() again during ingress_destroy(), setting eth0->miniq_ingress to NULL, so ingress packets on eth0 will not find filter Y in sch_handle_ingress(). This is just one of the possible consequences of concurrently accessing miniq_{in,e}gress pointers. Fixes: 7a096d579e8e ("net: sched: ingress: set 'unlocked' flag for Qdisc ops") Fixes: 87f373921c4e ("net: sched: ingress: set 'unlocked' flag for clsact Qdisc ops") Reported-by: syzbot+b53a9c0d1ea4ad62da8b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/0000000000006cf87705f79acf1a@google.com/ Cc: Hillf Danton <hdanton@sina.com> Cc: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-06-11 03:30:25 +00:00
__qdisc_destroy(qdisc);
}
EXPORT_SYMBOL(qdisc_put);
/* Version of qdisc_put() that is called with rtnl mutex unlocked.
* Intended to be used as optimization, this function only takes rtnl lock if
* qdisc reference counter reached zero.
*/
void qdisc_put_unlocked(struct Qdisc *qdisc)
{
if (qdisc->flags & TCQ_F_BUILTIN ||
!refcount_dec_and_rtnl_lock(&qdisc->refcnt))
return;
net/sched: qdisc_destroy() old ingress and clsact Qdiscs before grafting mini_Qdisc_pair::p_miniq is a double pointer to mini_Qdisc, initialized in ingress_init() to point to net_device::miniq_ingress. ingress Qdiscs access this per-net_device pointer in mini_qdisc_pair_swap(). Similar for clsact Qdiscs and miniq_egress. Unfortunately, after introducing RTNL-unlocked RTM_{NEW,DEL,GET}TFILTER requests (thanks Hillf Danton for the hint), when replacing ingress or clsact Qdiscs, for example, the old Qdisc ("@old") could access the same miniq_{in,e}gress pointer(s) concurrently with the new Qdisc ("@new"), causing race conditions [1] including a use-after-free bug in mini_qdisc_pair_swap() reported by syzbot: BUG: KASAN: slab-use-after-free in mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 Write of size 8 at addr ffff888045b31308 by task syz-executor690/14901 ... Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106 print_address_description.constprop.0+0x2c/0x3c0 mm/kasan/report.c:319 print_report mm/kasan/report.c:430 [inline] kasan_report+0x11c/0x130 mm/kasan/report.c:536 mini_qdisc_pair_swap+0x1c2/0x1f0 net/sched/sch_generic.c:1573 tcf_chain_head_change_item net/sched/cls_api.c:495 [inline] tcf_chain0_head_change.isra.0+0xb9/0x120 net/sched/cls_api.c:509 tcf_chain_tp_insert net/sched/cls_api.c:1826 [inline] tcf_chain_tp_insert_unique net/sched/cls_api.c:1875 [inline] tc_new_tfilter+0x1de6/0x2290 net/sched/cls_api.c:2266 ... @old and @new should not affect each other. In other words, @old should never modify miniq_{in,e}gress after @new, and @new should not update @old's RCU state. Fixing without changing sch_api.c turned out to be difficult (please refer to Closes: for discussions). Instead, make sure @new's first call always happen after @old's last call (in {ingress,clsact}_destroy()) has finished: In qdisc_graft(), return -EBUSY if @old has any ongoing filter requests, and call qdisc_destroy() for @old before grafting @new. Introduce qdisc_refcount_dec_if_one() as the counterpart of qdisc_refcount_inc_nz() used for filter requests. Introduce a non-static version of qdisc_destroy() that does a TCQ_F_BUILTIN check, just like qdisc_put() etc. Depends on patch "net/sched: Refactor qdisc_graft() for ingress and clsact Qdiscs". [1] To illustrate, the syzkaller reproducer adds ingress Qdiscs under TC_H_ROOT (no longer possible after commit c7cfbd115001 ("net/sched: sch_ingress: Only create under TC_H_INGRESS")) on eth0 that has 8 transmission queues: Thread 1 creates ingress Qdisc A (containing mini Qdisc a1 and a2), then adds a flower filter X to A. Thread 2 creates another ingress Qdisc B (containing mini Qdisc b1 and b2) to replace A, then adds a flower filter Y to B. Thread 1 A's refcnt Thread 2 RTM_NEWQDISC (A, RTNL-locked) qdisc_create(A) 1 qdisc_graft(A) 9 RTM_NEWTFILTER (X, RTNL-unlocked) __tcf_qdisc_find(A) 10 tcf_chain0_head_change(A) mini_qdisc_pair_swap(A) (1st) | | RTM_NEWQDISC (B, RTNL-locked) RCU sync 2 qdisc_graft(B) | 1 notify_and_destroy(A) | tcf_block_release(A) 0 RTM_NEWTFILTER (Y, RTNL-unlocked) qdisc_destroy(A) tcf_chain0_head_change(B) tcf_chain0_head_change_cb_del(A) mini_qdisc_pair_swap(B) (2nd) mini_qdisc_pair_swap(A) (3rd) | ... ... Here, B calls mini_qdisc_pair_swap(), pointing eth0->miniq_ingress to its mini Qdisc, b1. Then, A calls mini_qdisc_pair_swap() again during ingress_destroy(), setting eth0->miniq_ingress to NULL, so ingress packets on eth0 will not find filter Y in sch_handle_ingress(). This is just one of the possible consequences of concurrently accessing miniq_{in,e}gress pointers. Fixes: 7a096d579e8e ("net: sched: ingress: set 'unlocked' flag for Qdisc ops") Fixes: 87f373921c4e ("net: sched: ingress: set 'unlocked' flag for clsact Qdisc ops") Reported-by: syzbot+b53a9c0d1ea4ad62da8b@syzkaller.appspotmail.com Closes: https://lore.kernel.org/r/0000000000006cf87705f79acf1a@google.com/ Cc: Hillf Danton <hdanton@sina.com> Cc: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: Peilin Ye <peilin.ye@bytedance.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2023-06-11 03:30:25 +00:00
__qdisc_destroy(qdisc);
rtnl_unlock();
}
EXPORT_SYMBOL(qdisc_put_unlocked);
/* Attach toplevel qdisc to device queue. */
struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
struct Qdisc *qdisc)
{
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
struct Qdisc *oqdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
spinlock_t *root_lock;
root_lock = qdisc_lock(oqdisc);
spin_lock_bh(root_lock);
/* ... and graft new one */
if (qdisc == NULL)
qdisc = &noop_qdisc;
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc);
rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc);
spin_unlock_bh(root_lock);
return oqdisc;
}
net_sched: implement a root container qdisc sch_mqprio This implements a mqprio queueing discipline that by default creates a pfifo_fast qdisc per tx queue and provides the needed configuration interface. Using the mqprio qdisc the number of tcs currently in use along with the range of queues alloted to each class can be configured. By default skbs are mapped to traffic classes using the skb priority. This mapping is configurable. Configurable parameters, struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_BITMASK + 1]; __u8 hw; __u16 count[TC_MAX_QUEUE]; __u16 offset[TC_MAX_QUEUE]; }; Here the count/offset pairing give the queue alignment and the prio_tc_map gives the mapping from skb->priority to tc. The hw bit determines if the hardware should configure the count and offset values. If the hardware bit is set then the operation will fail if the hardware does not implement the ndo_setup_tc operation. This is to avoid undetermined states where the hardware may or may not control the queue mapping. Also minimal bounds checking is done on the count/offset to verify a queue does not exceed num_tx_queues and that queue ranges do not overlap. Otherwise it is left to user policy or hardware configuration to create useful mappings. It is expected that hardware QOS schemes can be implemented by creating appropriate mappings of queues in ndo_tc_setup(). One expected use case is drivers will use the ndo_setup_tc to map queue ranges onto 802.1Q traffic classes. This provides a generic mechanism to map network traffic onto these traffic classes and removes the need for lower layer drivers to know specifics about traffic types. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-17 08:06:09 +00:00
EXPORT_SYMBOL(dev_graft_qdisc);
net/sched: fix netdevice reference leaks in attach_default_qdiscs() In attach_default_qdiscs(), if a dev has multiple queues and queue 0 fails to attach qdisc because there is no memory in attach_one_default_qdisc(). Then dev->qdisc will be noop_qdisc by default. But the other queues may be able to successfully attach to default qdisc. In this case, the fallback to noqueue process will be triggered. If the original attached qdisc is not released and a new one is directly attached, this will cause netdevice reference leaks. The following is the bug log: veth0: default qdisc (fq_codel) fail, fallback to noqueue unregister_netdevice: waiting for veth0 to become free. Usage count = 32 leaked reference. qdisc_alloc+0x12e/0x210 qdisc_create_dflt+0x62/0x140 attach_one_default_qdisc.constprop.41+0x44/0x70 dev_activate+0x128/0x290 __dev_open+0x12a/0x190 __dev_change_flags+0x1a2/0x1f0 dev_change_flags+0x23/0x60 do_setlink+0x332/0x1150 __rtnl_newlink+0x52f/0x8e0 rtnl_newlink+0x43/0x70 rtnetlink_rcv_msg+0x140/0x3b0 netlink_rcv_skb+0x50/0x100 netlink_unicast+0x1bb/0x290 netlink_sendmsg+0x37c/0x4e0 sock_sendmsg+0x5f/0x70 ____sys_sendmsg+0x208/0x280 Fix this bug by clearing any non-noop qdiscs that may have been assigned before trying to re-attach. Fixes: bf6dba76d278 ("net: sched: fallback to qdisc noqueue if default qdisc setup fail") Signed-off-by: Wang Hai <wanghai38@huawei.com> Link: https://lore.kernel.org/r/20220826090055.24424-1-wanghai38@huawei.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-08-26 09:00:55 +00:00
static void shutdown_scheduler_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc_default)
{
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
net/sched: fix netdevice reference leaks in attach_default_qdiscs() In attach_default_qdiscs(), if a dev has multiple queues and queue 0 fails to attach qdisc because there is no memory in attach_one_default_qdisc(). Then dev->qdisc will be noop_qdisc by default. But the other queues may be able to successfully attach to default qdisc. In this case, the fallback to noqueue process will be triggered. If the original attached qdisc is not released and a new one is directly attached, this will cause netdevice reference leaks. The following is the bug log: veth0: default qdisc (fq_codel) fail, fallback to noqueue unregister_netdevice: waiting for veth0 to become free. Usage count = 32 leaked reference. qdisc_alloc+0x12e/0x210 qdisc_create_dflt+0x62/0x140 attach_one_default_qdisc.constprop.41+0x44/0x70 dev_activate+0x128/0x290 __dev_open+0x12a/0x190 __dev_change_flags+0x1a2/0x1f0 dev_change_flags+0x23/0x60 do_setlink+0x332/0x1150 __rtnl_newlink+0x52f/0x8e0 rtnl_newlink+0x43/0x70 rtnetlink_rcv_msg+0x140/0x3b0 netlink_rcv_skb+0x50/0x100 netlink_unicast+0x1bb/0x290 netlink_sendmsg+0x37c/0x4e0 sock_sendmsg+0x5f/0x70 ____sys_sendmsg+0x208/0x280 Fix this bug by clearing any non-noop qdiscs that may have been assigned before trying to re-attach. Fixes: bf6dba76d278 ("net: sched: fallback to qdisc noqueue if default qdisc setup fail") Signed-off-by: Wang Hai <wanghai38@huawei.com> Link: https://lore.kernel.org/r/20220826090055.24424-1-wanghai38@huawei.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-08-26 09:00:55 +00:00
struct Qdisc *qdisc_default = _qdisc_default;
if (qdisc) {
rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc_default);
net/sched: fix netdevice reference leaks in attach_default_qdiscs() In attach_default_qdiscs(), if a dev has multiple queues and queue 0 fails to attach qdisc because there is no memory in attach_one_default_qdisc(). Then dev->qdisc will be noop_qdisc by default. But the other queues may be able to successfully attach to default qdisc. In this case, the fallback to noqueue process will be triggered. If the original attached qdisc is not released and a new one is directly attached, this will cause netdevice reference leaks. The following is the bug log: veth0: default qdisc (fq_codel) fail, fallback to noqueue unregister_netdevice: waiting for veth0 to become free. Usage count = 32 leaked reference. qdisc_alloc+0x12e/0x210 qdisc_create_dflt+0x62/0x140 attach_one_default_qdisc.constprop.41+0x44/0x70 dev_activate+0x128/0x290 __dev_open+0x12a/0x190 __dev_change_flags+0x1a2/0x1f0 dev_change_flags+0x23/0x60 do_setlink+0x332/0x1150 __rtnl_newlink+0x52f/0x8e0 rtnl_newlink+0x43/0x70 rtnetlink_rcv_msg+0x140/0x3b0 netlink_rcv_skb+0x50/0x100 netlink_unicast+0x1bb/0x290 netlink_sendmsg+0x37c/0x4e0 sock_sendmsg+0x5f/0x70 ____sys_sendmsg+0x208/0x280 Fix this bug by clearing any non-noop qdiscs that may have been assigned before trying to re-attach. Fixes: bf6dba76d278 ("net: sched: fallback to qdisc noqueue if default qdisc setup fail") Signed-off-by: Wang Hai <wanghai38@huawei.com> Link: https://lore.kernel.org/r/20220826090055.24424-1-wanghai38@huawei.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-08-26 09:00:55 +00:00
qdisc_put(qdisc);
}
}
static void attach_one_default_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_unused)
{
struct Qdisc *qdisc;
const struct Qdisc_ops *ops = default_qdisc_ops;
if (dev->priv_flags & IFF_NO_QUEUE)
ops = &noqueue_qdisc_ops;
net: sch_generic: Use pfifo_fast as fallback scheduler for CAN hardware There is networking hardware that isn't based on Ethernet for layers 1 and 2. For example CAN. CAN is a multi-master serial bus standard for connecting Electronic Control Units [ECUs] also known as nodes. A frame on the CAN bus carries up to 8 bytes of payload. Frame corruption is detected by a CRC. However frame loss due to corruption is possible, but a quite unusual phenomenon. While fq_codel works great for TCP/IP, it doesn't for CAN. There are a lot of legacy protocols on top of CAN, which are not build with flow control or high CAN frame drop rates in mind. When using fq_codel, as soon as the queue reaches a certain delay based length, skbs from the head of the queue are silently dropped. Silently meaning that the user space using a send() or similar syscall doesn't get an error. However TCP's flow control algorithm will detect dropped packages and adjust the bandwidth accordingly. When using fq_codel and sending raw frames over CAN, which is the common use case, the user space thinks the package has been sent without problems, because send() returned without an error. pfifo_fast will drop skbs, if the queue length exceeds the maximum. But with this scheduler the skbs at the tail are dropped, an error (-ENOBUFS) is propagated to user space. So that the user space can slow down the package generation. On distributions, where fq_codel is made default via CONFIG_DEFAULT_NET_SCH during compile time, or set default during runtime with sysctl net.core.default_qdisc (see [1]), we get a bad user experience. In my test case with pfifo_fast, I can transfer thousands of million CAN frames without a frame drop. On the other hand with fq_codel there is more then one lost CAN frame per thousand frames. As pointed out fq_codel is not suited for CAN hardware, so this patch changes attach_one_default_qdisc() to use pfifo_fast for "ARPHRD_CAN" network devices. During transition of a netdev from down to up state the default queuing discipline is attached by attach_default_qdiscs() with the help of attach_one_default_qdisc(). This patch modifies attach_one_default_qdisc() to attach the pfifo_fast (pfifo_fast_ops) if the network device type is "ARPHRD_CAN". [1] https://github.com/systemd/systemd/issues/9194 Suggested-by: Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de> Signed-off-by: Vincent Prince <vincent.prince.fr@gmail.com> Acked-by: Dave Taht <dave.taht@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-10-23 13:44:20 +00:00
else if(dev->type == ARPHRD_CAN)
ops = &pfifo_fast_ops;
qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL);
if (!qdisc)
return;
if (!netif_is_multiqueue(dev))
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;
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc);
}
static void attach_default_qdiscs(struct net_device *dev)
{
struct netdev_queue *txq;
struct Qdisc *qdisc;
txq = netdev_get_tx_queue(dev, 0);
if (!netif_is_multiqueue(dev) ||
dev->priv_flags & IFF_NO_QUEUE) {
netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
qdisc = rtnl_dereference(txq->qdisc_sleeping);
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
rcu_assign_pointer(dev->qdisc, qdisc);
qdisc_refcount_inc(qdisc);
} else {
qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL);
if (qdisc) {
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
rcu_assign_pointer(dev->qdisc, qdisc);
qdisc->ops->attach(qdisc);
}
}
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
qdisc = rtnl_dereference(dev->qdisc);
/* Detect default qdisc setup/init failed and fallback to "noqueue" */
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
if (qdisc == &noop_qdisc) {
netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n",
default_qdisc_ops->id, noqueue_qdisc_ops.id);
net/sched: fix netdevice reference leaks in attach_default_qdiscs() In attach_default_qdiscs(), if a dev has multiple queues and queue 0 fails to attach qdisc because there is no memory in attach_one_default_qdisc(). Then dev->qdisc will be noop_qdisc by default. But the other queues may be able to successfully attach to default qdisc. In this case, the fallback to noqueue process will be triggered. If the original attached qdisc is not released and a new one is directly attached, this will cause netdevice reference leaks. The following is the bug log: veth0: default qdisc (fq_codel) fail, fallback to noqueue unregister_netdevice: waiting for veth0 to become free. Usage count = 32 leaked reference. qdisc_alloc+0x12e/0x210 qdisc_create_dflt+0x62/0x140 attach_one_default_qdisc.constprop.41+0x44/0x70 dev_activate+0x128/0x290 __dev_open+0x12a/0x190 __dev_change_flags+0x1a2/0x1f0 dev_change_flags+0x23/0x60 do_setlink+0x332/0x1150 __rtnl_newlink+0x52f/0x8e0 rtnl_newlink+0x43/0x70 rtnetlink_rcv_msg+0x140/0x3b0 netlink_rcv_skb+0x50/0x100 netlink_unicast+0x1bb/0x290 netlink_sendmsg+0x37c/0x4e0 sock_sendmsg+0x5f/0x70 ____sys_sendmsg+0x208/0x280 Fix this bug by clearing any non-noop qdiscs that may have been assigned before trying to re-attach. Fixes: bf6dba76d278 ("net: sched: fallback to qdisc noqueue if default qdisc setup fail") Signed-off-by: Wang Hai <wanghai38@huawei.com> Link: https://lore.kernel.org/r/20220826090055.24424-1-wanghai38@huawei.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
2022-08-26 09:00:55 +00:00
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
dev->priv_flags |= IFF_NO_QUEUE;
netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
qdisc = rtnl_dereference(txq->qdisc_sleeping);
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
rcu_assign_pointer(dev->qdisc, qdisc);
qdisc_refcount_inc(qdisc);
dev->priv_flags ^= IFF_NO_QUEUE;
}
#ifdef CONFIG_NET_SCHED
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
if (qdisc != &noop_qdisc)
qdisc_hash_add(qdisc, false);
#endif
}
static void transition_one_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_need_watchdog)
{
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
struct Qdisc *new_qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
int *need_watchdog_p = _need_watchdog;
if (!(new_qdisc->flags & TCQ_F_BUILTIN))
clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state);
rcu_assign_pointer(dev_queue->qdisc, new_qdisc);
if (need_watchdog_p) {
WRITE_ONCE(dev_queue->trans_start, 0);
*need_watchdog_p = 1;
}
}
void dev_activate(struct net_device *dev)
{
int need_watchdog;
/* No queueing discipline is attached to device;
* create default one for devices, which need queueing
* and noqueue_qdisc for virtual interfaces
*/
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
if (rtnl_dereference(dev->qdisc) == &noop_qdisc)
attach_default_qdiscs(dev);
if (!netif_carrier_ok(dev))
/* Delay activation until next carrier-on event */
return;
need_watchdog = 0;
netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog);
if (dev_ingress_queue(dev))
transition_one_qdisc(dev, dev_ingress_queue(dev), NULL);
if (need_watchdog) {
netif_trans_update(dev);
dev_watchdog_up(dev);
}
}
net_sched: implement a root container qdisc sch_mqprio This implements a mqprio queueing discipline that by default creates a pfifo_fast qdisc per tx queue and provides the needed configuration interface. Using the mqprio qdisc the number of tcs currently in use along with the range of queues alloted to each class can be configured. By default skbs are mapped to traffic classes using the skb priority. This mapping is configurable. Configurable parameters, struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_BITMASK + 1]; __u8 hw; __u16 count[TC_MAX_QUEUE]; __u16 offset[TC_MAX_QUEUE]; }; Here the count/offset pairing give the queue alignment and the prio_tc_map gives the mapping from skb->priority to tc. The hw bit determines if the hardware should configure the count and offset values. If the hardware bit is set then the operation will fail if the hardware does not implement the ndo_setup_tc operation. This is to avoid undetermined states where the hardware may or may not control the queue mapping. Also minimal bounds checking is done on the count/offset to verify a queue does not exceed num_tx_queues and that queue ranges do not overlap. Otherwise it is left to user policy or hardware configuration to create useful mappings. It is expected that hardware QOS schemes can be implemented by creating appropriate mappings of queues in ndo_tc_setup(). One expected use case is drivers will use the ndo_setup_tc to map queue ranges onto 802.1Q traffic classes. This provides a generic mechanism to map network traffic onto these traffic classes and removes the need for lower layer drivers to know specifics about traffic types. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-17 08:06:09 +00:00
EXPORT_SYMBOL(dev_activate);
static void qdisc_deactivate(struct Qdisc *qdisc)
{
if (qdisc->flags & TCQ_F_BUILTIN)
return;
set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
}
static void dev_deactivate_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc_default)
{
struct Qdisc *qdisc_default = _qdisc_default;
struct Qdisc *qdisc;
qdisc = rtnl_dereference(dev_queue->qdisc);
if (qdisc) {
qdisc_deactivate(qdisc);
rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
}
}
static void dev_reset_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_unused)
{
struct Qdisc *qdisc;
bool nolock;
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
if (!qdisc)
return;
nolock = qdisc->flags & TCQ_F_NOLOCK;
if (nolock)
spin_lock_bh(&qdisc->seqlock);
spin_lock_bh(qdisc_lock(qdisc));
qdisc_reset(qdisc);
spin_unlock_bh(qdisc_lock(qdisc));
net: sched: fix tx action rescheduling issue during deactivation Currently qdisc_run() checks the STATE_DEACTIVATED of lockless qdisc before calling __qdisc_run(), which ultimately clear the STATE_MISSED when all the skb is dequeued. If STATE_DEACTIVATED is set before clearing STATE_MISSED, there may be rescheduling of net_tx_action() at the end of qdisc_run_end(), see below: CPU0(net_tx_atcion) CPU1(__dev_xmit_skb) CPU2(dev_deactivate) . . . . set STATE_MISSED . . __netif_schedule() . . . set STATE_DEACTIVATED . . qdisc_reset() . . . .<--------------- . synchronize_net() clear __QDISC_STATE_SCHED | . . . | . . . | . some_qdisc_is_busy() . | . return *false* . | . . test STATE_DEACTIVATED | . . __qdisc_run() *not* called | . . . | . . test STATE_MISS | . . __netif_schedule()--------| . . . . . . . . __qdisc_run() is not called by net_tx_atcion() in CPU0 because CPU2 has set STATE_DEACTIVATED flag during dev_deactivate(), and STATE_MISSED is only cleared in __qdisc_run(), __netif_schedule is called at the end of qdisc_run_end(), causing tx action rescheduling problem. qdisc_run() called by net_tx_action() runs in the softirq context, which should has the same semantic as the qdisc_run() called by __dev_xmit_skb() protected by rcu_read_lock_bh(). And there is a synchronize_net() between STATE_DEACTIVATED flag being set and qdisc_reset()/some_qdisc_is_busy in dev_deactivate(), we can safely bail out for the deactived lockless qdisc in net_tx_action(), and qdisc_reset() will reset all skb not dequeued yet. So add the rcu_read_lock() explicitly to protect the qdisc_run() and do the STATE_DEACTIVATED checking in net_tx_action() before calling qdisc_run_begin(). Another option is to do the checking in the qdisc_run_end(), but it will add unnecessary overhead for non-tx_action case, because __dev_queue_xmit() will not see qdisc with STATE_DEACTIVATED after synchronize_net(), the qdisc with STATE_DEACTIVATED can only be seen by net_tx_action() because of __netif_schedule(). The STATE_DEACTIVATED checking in qdisc_run() is to avoid race between net_tx_action() and qdisc_reset(), see: commit d518d2ed8640 ("net/sched: fix race between deactivation and dequeue for NOLOCK qdisc"). As the bailout added above for deactived lockless qdisc in net_tx_action() provides better protection for the race without calling qdisc_run() at all, so remove the STATE_DEACTIVATED checking in qdisc_run(). After qdisc_reset(), there is no skb in qdisc to be dequeued, so clear the STATE_MISSED in dev_reset_queue() too. Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> V8: Clearing STATE_MISSED before calling __netif_schedule() has avoid the endless rescheduling problem, but there may still be a unnecessary rescheduling, so adjust the commit log. Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-14 03:17:00 +00:00
if (nolock) {
clear_bit(__QDISC_STATE_MISSED, &qdisc->state);
net: sched: implement TCQ_F_CAN_BYPASS for lockless qdisc Currently pfifo_fast has both TCQ_F_CAN_BYPASS and TCQ_F_NOLOCK flag set, but queue discipline by-pass does not work for lockless qdisc because skb is always enqueued to qdisc even when the qdisc is empty, see __dev_xmit_skb(). This patch calls sch_direct_xmit() to transmit the skb directly to the driver for empty lockless qdisc, which aviod enqueuing and dequeuing operation. As qdisc->empty is not reliable to indicate a empty qdisc because there is a time window between enqueuing and setting qdisc->empty. So we use the MISSED state added in commit a90c57f2cedd ("net: sched: fix packet stuck problem for lockless qdisc"), which indicate there is lock contention, suggesting that it is better not to do the qdisc bypass in order to avoid packet out of order problem. In order to make MISSED state reliable to indicate a empty qdisc, we need to ensure that testing and clearing of MISSED state is within the protection of qdisc->seqlock, only setting MISSED state can be done without the protection of qdisc->seqlock. A MISSED state testing is added without the protection of qdisc->seqlock to aviod doing unnecessary spin_trylock() for contention case. As the enqueuing is not within the protection of qdisc->seqlock, there is still a potential data race as mentioned by Jakub [1]: thread1 thread2 thread3 qdisc_run_begin() # true qdisc_run_begin(q) set(MISSED) pfifo_fast_dequeue clear(MISSED) # recheck the queue qdisc_run_end() enqueue skb1 qdisc empty # true qdisc_run_begin() # true sch_direct_xmit() # skb2 qdisc_run_begin() set(MISSED) When above happens, skb1 enqueued by thread2 is transmited after skb2 is transmited by thread3 because MISSED state setting and enqueuing is not under the qdisc->seqlock. If qdisc bypass is disabled, skb1 has better chance to be transmited quicker than skb2. This patch does not take care of the above data race, because we view this as similar as below: Even at the same time CPU1 and CPU2 write the skb to two socket which both heading to the same qdisc, there is no guarantee that which skb will hit the qdisc first, because there is a lot of factor like interrupt/softirq/cache miss/scheduling afffecting that. There are below cases that need special handling: 1. When MISSED state is cleared before another round of dequeuing in pfifo_fast_dequeue(), and __qdisc_run() might not be able to dequeue all skb in one round and call __netif_schedule(), which might result in a non-empty qdisc without MISSED set. In order to avoid this, the MISSED state is set for lockless qdisc and __netif_schedule() will be called at the end of qdisc_run_end. 2. The MISSED state also need to be set for lockless qdisc instead of calling __netif_schedule() directly when requeuing a skb for a similar reason. 3. For netdev queue stopped case, the MISSED case need clearing while the netdev queue is stopped, otherwise there may be unnecessary __netif_schedule() calling. So a new DRAINING state is added to indicate this case, which also indicate a non-empty qdisc. 4. As there is already netif_xmit_frozen_or_stopped() checking in dequeue_skb() and sch_direct_xmit(), which are both within the protection of qdisc->seqlock, but the same checking in __dev_xmit_skb() is without the protection, which might cause empty indication of a lockless qdisc to be not reliable. So remove the checking in __dev_xmit_skb(), and the checking in the protection of qdisc->seqlock seems enough to avoid the cpu consumption problem for netdev queue stopped case. 1. https://lkml.org/lkml/2021/5/29/215 Acked-by: Jakub Kicinski <kuba@kernel.org> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> # flexcan Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2021-06-22 06:49:56 +00:00
clear_bit(__QDISC_STATE_DRAINING, &qdisc->state);
spin_unlock_bh(&qdisc->seqlock);
net: sched: fix tx action rescheduling issue during deactivation Currently qdisc_run() checks the STATE_DEACTIVATED of lockless qdisc before calling __qdisc_run(), which ultimately clear the STATE_MISSED when all the skb is dequeued. If STATE_DEACTIVATED is set before clearing STATE_MISSED, there may be rescheduling of net_tx_action() at the end of qdisc_run_end(), see below: CPU0(net_tx_atcion) CPU1(__dev_xmit_skb) CPU2(dev_deactivate) . . . . set STATE_MISSED . . __netif_schedule() . . . set STATE_DEACTIVATED . . qdisc_reset() . . . .<--------------- . synchronize_net() clear __QDISC_STATE_SCHED | . . . | . . . | . some_qdisc_is_busy() . | . return *false* . | . . test STATE_DEACTIVATED | . . __qdisc_run() *not* called | . . . | . . test STATE_MISS | . . __netif_schedule()--------| . . . . . . . . __qdisc_run() is not called by net_tx_atcion() in CPU0 because CPU2 has set STATE_DEACTIVATED flag during dev_deactivate(), and STATE_MISSED is only cleared in __qdisc_run(), __netif_schedule is called at the end of qdisc_run_end(), causing tx action rescheduling problem. qdisc_run() called by net_tx_action() runs in the softirq context, which should has the same semantic as the qdisc_run() called by __dev_xmit_skb() protected by rcu_read_lock_bh(). And there is a synchronize_net() between STATE_DEACTIVATED flag being set and qdisc_reset()/some_qdisc_is_busy in dev_deactivate(), we can safely bail out for the deactived lockless qdisc in net_tx_action(), and qdisc_reset() will reset all skb not dequeued yet. So add the rcu_read_lock() explicitly to protect the qdisc_run() and do the STATE_DEACTIVATED checking in net_tx_action() before calling qdisc_run_begin(). Another option is to do the checking in the qdisc_run_end(), but it will add unnecessary overhead for non-tx_action case, because __dev_queue_xmit() will not see qdisc with STATE_DEACTIVATED after synchronize_net(), the qdisc with STATE_DEACTIVATED can only be seen by net_tx_action() because of __netif_schedule(). The STATE_DEACTIVATED checking in qdisc_run() is to avoid race between net_tx_action() and qdisc_reset(), see: commit d518d2ed8640 ("net/sched: fix race between deactivation and dequeue for NOLOCK qdisc"). As the bailout added above for deactived lockless qdisc in net_tx_action() provides better protection for the race without calling qdisc_run() at all, so remove the STATE_DEACTIVATED checking in qdisc_run(). After qdisc_reset(), there is no skb in qdisc to be dequeued, so clear the STATE_MISSED in dev_reset_queue() too. Fixes: 6b3ba9146fe6 ("net: sched: allow qdiscs to handle locking") Acked-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com> V8: Clearing STATE_MISSED before calling __netif_schedule() has avoid the endless rescheduling problem, but there may still be a unnecessary rescheduling, so adjust the commit log. Signed-off-by: David S. Miller <davem@davemloft.net>
2021-05-14 03:17:00 +00:00
}
}
static bool some_qdisc_is_busy(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *dev_queue;
spinlock_t *root_lock;
struct Qdisc *q;
int val;
dev_queue = netdev_get_tx_queue(dev, i);
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
q = rtnl_dereference(dev_queue->qdisc_sleeping);
root_lock = qdisc_lock(q);
spin_lock_bh(root_lock);
val = (qdisc_is_running(q) ||
test_bit(__QDISC_STATE_SCHED, &q->state));
spin_unlock_bh(root_lock);
if (val)
return true;
}
return false;
}
/**
* dev_deactivate_many - deactivate transmissions on several devices
* @head: list of devices to deactivate
*
* This function returns only when all outstanding transmissions
* have completed, unless all devices are in dismantle phase.
*/
void dev_deactivate_many(struct list_head *head)
{
struct net_device *dev;
list_for_each_entry(dev, head, close_list) {
netdev_for_each_tx_queue(dev, dev_deactivate_queue,
&noop_qdisc);
if (dev_ingress_queue(dev))
dev_deactivate_queue(dev, dev_ingress_queue(dev),
&noop_qdisc);
dev_watchdog_down(dev);
}
/* Wait for outstanding qdisc-less dev_queue_xmit calls or
* outstanding qdisc enqueuing calls.
* This is avoided if all devices are in dismantle phase :
* Caller will call synchronize_net() for us
*/
synchronize_net();
list_for_each_entry(dev, head, close_list) {
netdev_for_each_tx_queue(dev, dev_reset_queue, NULL);
if (dev_ingress_queue(dev))
dev_reset_queue(dev, dev_ingress_queue(dev), NULL);
}
/* Wait for outstanding qdisc_run calls. */
list_for_each_entry(dev, head, close_list) {
while (some_qdisc_is_busy(dev)) {
/* wait_event() would avoid this sleep-loop but would
* require expensive checks in the fast paths of packet
* processing which isn't worth it.
*/
schedule_timeout_uninterruptible(1);
}
}
}
void dev_deactivate(struct net_device *dev)
{
LIST_HEAD(single);
list_add(&dev->close_list, &single);
dev_deactivate_many(&single);
list_del(&single);
}
net_sched: implement a root container qdisc sch_mqprio This implements a mqprio queueing discipline that by default creates a pfifo_fast qdisc per tx queue and provides the needed configuration interface. Using the mqprio qdisc the number of tcs currently in use along with the range of queues alloted to each class can be configured. By default skbs are mapped to traffic classes using the skb priority. This mapping is configurable. Configurable parameters, struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_BITMASK + 1]; __u8 hw; __u16 count[TC_MAX_QUEUE]; __u16 offset[TC_MAX_QUEUE]; }; Here the count/offset pairing give the queue alignment and the prio_tc_map gives the mapping from skb->priority to tc. The hw bit determines if the hardware should configure the count and offset values. If the hardware bit is set then the operation will fail if the hardware does not implement the ndo_setup_tc operation. This is to avoid undetermined states where the hardware may or may not control the queue mapping. Also minimal bounds checking is done on the count/offset to verify a queue does not exceed num_tx_queues and that queue ranges do not overlap. Otherwise it is left to user policy or hardware configuration to create useful mappings. It is expected that hardware QOS schemes can be implemented by creating appropriate mappings of queues in ndo_tc_setup(). One expected use case is drivers will use the ndo_setup_tc to map queue ranges onto 802.1Q traffic classes. This provides a generic mechanism to map network traffic onto these traffic classes and removes the need for lower layer drivers to know specifics about traffic types. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-17 08:06:09 +00:00
EXPORT_SYMBOL(dev_deactivate);
static int qdisc_change_tx_queue_len(struct net_device *dev,
struct netdev_queue *dev_queue)
{
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping);
const struct Qdisc_ops *ops = qdisc->ops;
if (ops->change_tx_queue_len)
return ops->change_tx_queue_len(qdisc, dev->tx_queue_len);
return 0;
}
void dev_qdisc_change_real_num_tx(struct net_device *dev,
unsigned int new_real_tx)
{
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
struct Qdisc *qdisc = rtnl_dereference(dev->qdisc);
if (qdisc->ops->change_real_num_tx)
qdisc->ops->change_real_num_tx(qdisc, new_real_tx);
}
void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx)
{
#ifdef CONFIG_NET_SCHED
struct net_device *dev = qdisc_dev(sch);
struct Qdisc *qdisc;
unsigned int i;
for (i = new_real_tx; i < dev->real_num_tx_queues; i++) {
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping);
/* Only update the default qdiscs we created,
* qdiscs with handles are always hashed.
*/
if (qdisc != &noop_qdisc && !qdisc->handle)
qdisc_hash_del(qdisc);
}
for (i = dev->real_num_tx_queues; i < new_real_tx; i++) {
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping);
if (qdisc != &noop_qdisc && !qdisc->handle)
qdisc_hash_add(qdisc, false);
}
#endif
}
EXPORT_SYMBOL(mq_change_real_num_tx);
int dev_qdisc_change_tx_queue_len(struct net_device *dev)
{
bool up = dev->flags & IFF_UP;
unsigned int i;
int ret = 0;
if (up)
dev_deactivate(dev);
for (i = 0; i < dev->num_tx_queues; i++) {
ret = qdisc_change_tx_queue_len(dev, &dev->_tx[i]);
/* TODO: revert changes on a partial failure */
if (ret)
break;
}
if (up)
dev_activate(dev);
return ret;
}
static void dev_init_scheduler_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc)
{
struct Qdisc *qdisc = _qdisc;
rcu_assign_pointer(dev_queue->qdisc, qdisc);
net: sched: add rcu annotations around qdisc->qdisc_sleeping syzbot reported a race around qdisc->qdisc_sleeping [1] It is time we add proper annotations to reads and writes to/from qdisc->qdisc_sleeping. [1] BUG: KCSAN: data-race in dev_graft_qdisc / qdisc_lookup_rcu read to 0xffff8881286fc618 of 8 bytes by task 6928 on cpu 1: qdisc_lookup_rcu+0x192/0x2c0 net/sched/sch_api.c:331 __tcf_qdisc_find+0x74/0x3c0 net/sched/cls_api.c:1174 tc_get_tfilter+0x18f/0x990 net/sched/cls_api.c:2547 rtnetlink_rcv_msg+0x7af/0x8c0 net/core/rtnetlink.c:6386 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd write to 0xffff8881286fc618 of 8 bytes by task 6912 on cpu 0: dev_graft_qdisc+0x4f/0x80 net/sched/sch_generic.c:1115 qdisc_graft+0x7d0/0xb60 net/sched/sch_api.c:1103 tc_modify_qdisc+0x712/0xf10 net/sched/sch_api.c:1693 rtnetlink_rcv_msg+0x807/0x8c0 net/core/rtnetlink.c:6395 netlink_rcv_skb+0x126/0x220 net/netlink/af_netlink.c:2546 rtnetlink_rcv+0x1c/0x20 net/core/rtnetlink.c:6413 netlink_unicast_kernel net/netlink/af_netlink.c:1339 [inline] netlink_unicast+0x56f/0x640 net/netlink/af_netlink.c:1365 netlink_sendmsg+0x665/0x770 net/netlink/af_netlink.c:1913 sock_sendmsg_nosec net/socket.c:724 [inline] sock_sendmsg net/socket.c:747 [inline] ____sys_sendmsg+0x375/0x4c0 net/socket.c:2503 ___sys_sendmsg net/socket.c:2557 [inline] __sys_sendmsg+0x1e3/0x270 net/socket.c:2586 __do_sys_sendmsg net/socket.c:2595 [inline] __se_sys_sendmsg net/socket.c:2593 [inline] __x64_sys_sendmsg+0x46/0x50 net/socket.c:2593 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 6912 Comm: syz-executor.5 Not tainted 6.4.0-rc3-syzkaller-00190-g0d85b27b0cc6 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/16/2023 Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@nvidia.com> Acked-by: Jamal Hadi Salim<jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2023-06-06 11:19:29 +00:00
rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc);
}
void dev_init_scheduler(struct net_device *dev)
{
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
rcu_assign_pointer(dev->qdisc, &noop_qdisc);
netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
if (dev_ingress_queue(dev))
dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
timer_setup(&dev->watchdog_timer, dev_watchdog, 0);
}
void dev_shutdown(struct net_device *dev)
{
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
if (dev_ingress_queue(dev))
shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
net_sched: add __rcu annotation to netdev->qdisc syzbot found a data-race [1] which lead me to add __rcu annotations to netdev->qdisc, and proper accessors to get LOCKDEP support. [1] BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 __rtnl_newlink net/core/rtnetlink.c:3489 [inline] rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 sock_sendmsg_nosec net/socket.c:705 [inline] sock_sendmsg net/socket.c:725 [inline] ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 ___sys_sendmsg net/socket.c:2467 [inline] __sys_sendmsg+0x195/0x230 net/socket.c:2496 __do_sys_sendmsg net/socket.c:2505 [inline] __se_sys_sendmsg net/socket.c:2503 [inline] __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: 470502de5bdb ("net: sched: unlock rules update API") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vlad Buslov <vladbu@mellanox.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2022-02-11 20:06:23 +00:00
qdisc_put(rtnl_dereference(dev->qdisc));
rcu_assign_pointer(dev->qdisc, &noop_qdisc);
WARN_ON(timer_pending(&dev->watchdog_timer));
}
/**
* psched_ratecfg_precompute__() - Pre-compute values for reciprocal division
* @rate: Rate to compute reciprocal division values of
* @mult: Multiplier for reciprocal division
* @shift: Shift for reciprocal division
*
* The multiplier and shift for reciprocal division by rate are stored
* in mult and shift.
*
* The deal here is to replace a divide by a reciprocal one
* in fast path (a reciprocal divide is a multiply and a shift)
*
* Normal formula would be :
* time_in_ns = (NSEC_PER_SEC * len) / rate_bps
*
* We compute mult/shift to use instead :
* time_in_ns = (len * mult) >> shift;
*
* We try to get the highest possible mult value for accuracy,
* but have to make sure no overflows will ever happen.
*
* reciprocal_value() is not used here it doesn't handle 64-bit values.
*/
static void psched_ratecfg_precompute__(u64 rate, u32 *mult, u8 *shift)
{
u64 factor = NSEC_PER_SEC;
*mult = 1;
*shift = 0;
if (rate <= 0)
return;
for (;;) {
*mult = div64_u64(factor, rate);
if (*mult & (1U << 31) || factor & (1ULL << 63))
break;
factor <<= 1;
(*shift)++;
}
}
void psched_ratecfg_precompute(struct psched_ratecfg *r,
const struct tc_ratespec *conf,
u64 rate64)
{
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
net_sched: restore "mpu xxx" handling commit 56b765b79e9a ("htb: improved accuracy at high rates") broke "overhead X", "linklayer atm" and "mpu X" attributes. "overhead X" and "linklayer atm" have already been fixed. This restores the "mpu X" handling, as might be used by DOCSIS or Ethernet shaping: tc class add ... htb rate X overhead 4 mpu 64 The code being fixed is used by htb, tbf and act_police. Cake has its own mpu handling. qdisc_calculate_pkt_len still uses the size table containing values adjusted for mpu by user space. iproute2 tc has always passed mpu into the kernel via a tc_ratespec structure, but the kernel never directly acted on it, merely stored it so that it could be read back by `tc class show`. Rather, tc would generate length-to-time tables that included the mpu (and linklayer) in their construction, and the kernel used those tables. Since v3.7, the tables were no longer used. Along with "mpu", this also broke "overhead" and "linklayer" which were fixed in 01cb71d2d47b ("net_sched: restore "overhead xxx" handling", v3.10) and 8a8e3d84b171 ("net_sched: restore "linklayer atm" handling", v3.11). "overhead" was fixed by simply restoring use of tc_ratespec::overhead - this had originally been used by the kernel but was initially omitted from the new non-table-based calculations. "linklayer" had been handled in the table like "mpu", but the mode was not originally passed in tc_ratespec. The new implementation was made to handle it by getting new versions of tc to pass the mode in an extended tc_ratespec, and for older versions of tc the table contents were analysed at load time to deduce linklayer. As "mpu" has always been given to the kernel in tc_ratespec, accompanying the mpu-based table, we can restore system functionality with no userspace change by making the kernel act on the tc_ratespec value. Fixes: 56b765b79e9a ("htb: improved accuracy at high rates") Signed-off-by: Kevin Bracey <kevin@bracey.fi> Cc: Eric Dumazet <edumazet@google.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: Vimalkumar <j.vimal@gmail.com> Link: https://lore.kernel.org/r/20220112170210.1014351-1-kevin@bracey.fi Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2022-01-12 17:02:10 +00:00
r->mpu = conf->mpu;
r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift);
}
EXPORT_SYMBOL(psched_ratecfg_precompute);
void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64)
{
r->rate_pkts_ps = pktrate64;
psched_ratecfg_precompute__(r->rate_pkts_ps, &r->mult, &r->shift);
}
EXPORT_SYMBOL(psched_ppscfg_precompute);
void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
struct tcf_proto *tp_head)
{
/* Protected with chain0->filter_chain_lock.
* Can't access chain directly because tp_head can be NULL.
*/
struct mini_Qdisc *miniq_old =
rcu_dereference_protected(*miniqp->p_miniq, 1);
struct mini_Qdisc *miniq;
if (!tp_head) {
RCU_INIT_POINTER(*miniqp->p_miniq, NULL);
} else {
miniq = miniq_old != &miniqp->miniq1 ?
&miniqp->miniq1 : &miniqp->miniq2;
/* We need to make sure that readers won't see the miniq
* we are about to modify. So ensure that at least one RCU
* grace period has elapsed since the miniq was made
* inactive.
*/
if (IS_ENABLED(CONFIG_PREEMPT_RT))
cond_synchronize_rcu(miniq->rcu_state);
else if (!poll_state_synchronize_rcu(miniq->rcu_state))
synchronize_rcu_expedited();
miniq->filter_list = tp_head;
rcu_assign_pointer(*miniqp->p_miniq, miniq);
}
if (miniq_old)
/* This is counterpart of the rcu sync above. We need to
* block potential new user of miniq_old until all readers
* are not seeing it.
*/
miniq_old->rcu_state = start_poll_synchronize_rcu();
}
EXPORT_SYMBOL(mini_qdisc_pair_swap);
void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp,
struct tcf_block *block)
{
miniqp->miniq1.block = block;
miniqp->miniq2.block = block;
}
EXPORT_SYMBOL(mini_qdisc_pair_block_init);
void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
struct mini_Qdisc __rcu **p_miniq)
{
miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats;
miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats;
miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats;
miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats;
miniqp->miniq1.rcu_state = get_state_synchronize_rcu();
miniqp->miniq2.rcu_state = miniqp->miniq1.rcu_state;
miniqp->p_miniq = p_miniq;
}
EXPORT_SYMBOL(mini_qdisc_pair_init);