UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/net/sched/sch_generic.c

1393 lines
33 KiB
C
Raw Normal View History

Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/*
* net/sched/sch_generic.c Generic packet scheduler routines.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* 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 16:04:11 +08:00
#include <linux/slab.h>
net_sched: make dev_trans_start return vlan's real dev trans_start Vlan devices are LLTX and don't update their own trans_start, so if dev_trans_start has to be called with a vlan device then 0 or a stale value will be returned. Currently the bonding is the only such user, and it's needed for proper arp monitoring when the slaves are vlans. Fix this by extracting the vlan's real device trans_start. Suggested-by: David Miller <davem@davemloft.net> Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Acked-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-04 04:07:47 +08:00
#include <linux/if_vlan.h>
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
#include <linux/skb_array.h>
net_sched: use macvlan real dev trans_start in dev_trans_start() Macvlan devices are similar to vlans and do not update their own trans_start. In order for arp monitoring to work for a bond device when the slaves are macvlans, obtain its real device. Signed-off-by: Chris Dion <christopher.dion@dell.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-06 23:50:28 +08:00
#include <linux/if_macvlan.h>
sch: make htb_rate_cfg and functions around that generic As it is going to be used in tbf as well, push these to generic code. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 08:12:03 +08:00
#include <net/sch_generic.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include <net/pkt_sched.h>
net: add a noref bit on skb dst Use low order bit of skb->_skb_dst to tell dst is not refcounted. Change _skb_dst to _skb_refdst to make sure all uses are catched. skb_dst() returns the dst, regardless of noref bit set or not, but with a lockdep check to make sure a noref dst is not given if current user is not rcu protected. New skb_dst_set_noref() helper to set an notrefcounted dst on a skb. (with lockdep check) skb_dst_drop() drops a reference only if skb dst was refcounted. skb_dst_force() helper is used to force a refcount on dst, when skb is queued and not anymore RCU protected. Use skb_dst_force() in __sk_add_backlog(), __dev_xmit_skb() if !IFF_XMIT_DST_RELEASE or skb enqueued on qdisc queue, in sock_queue_rcv_skb(), in __nf_queue(). Use skb_dst_force() in dev_requeue_skb(). Note: dst_use_noref() still dirties dst, we might transform it later to do one dirtying per jiffies. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-05-12 07:19:48 +08:00
#include <net/dst.h>
qdisc: add tracepoint qdisc:qdisc_dequeue for dequeued SKBs The main purpose of this tracepoint is to monitor bulk dequeue in the network qdisc layer, as it cannot be deducted from the existing qdisc stats. The txq_state can be used for determining the reason for zero packet dequeues, see enum netdev_queue_state_t. Notice all packets doesn't necessary activate this tracepoint. As qdiscs with flag TCQ_F_CAN_BYPASS, can directly invoke sch_direct_xmit() when qdisc_qlen is zero. Remember that perf record supports filters like: perf record -e qdisc:qdisc_dequeue \ --filter 'ifindex == 4 && (packets > 1 || txq_state > 0)' Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 03:11:03 +08:00
#include <trace/events/qdisc.h>
net: Add asynchronous callbacks for xfrm on layer 2. This patch implements asynchronous crypto callbacks and a backlog handler that can be used when IPsec is done at layer 2 in the TX path. It also extends the skb validate functions so that we can update the driver transmit return codes based on async crypto operation or to indicate that we queued the packet in a backlog queue. Joint work with: Aviv Heller <avivh@mellanox.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-12-20 17:41:36 +08:00
#include <net/xfrm.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
qdisc: fix build with !CONFIG_NET_SCHED Multiqueue scheduler refers to default_qdisc_ops; therefore the variable definition needs to be moved to handle case where net scheduler API is not available. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-01 01:15:33 +08:00
/* Qdisc to use by default */
const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
EXPORT_SYMBOL(default_qdisc_ops);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Main transmission queue. */
[NET_SCHED]: Eliminate qdisc_tree_lock Since we're now holding the rtnl during the entire dump operation, we can remove qdisc_tree_lock, whose only purpose is to protect dump callbacks from concurrent changes to the qdisc tree. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-17 08:02:10 +08:00
/* Modifications to data participating in scheduling must be protected with
pkt_sched: Use qdisc_lock() on already sampled root qdisc. Based upon a bug report by Jeff Kirsher. Don't use qdisc_root_lock() in these cases as the root qdisc could have been changed, and we'd thus lock the wrong object. Tested by Emil S Tantilov who confirms that this seems to fix the problem. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-03 11:02:43 +08:00
* qdisc_lock(qdisc) spinlock.
[NET_SCHED]: Eliminate qdisc_tree_lock Since we're now holding the rtnl during the entire dump operation, we can remove qdisc_tree_lock, whose only purpose is to protect dump callbacks from concurrent changes to the qdisc tree. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-17 08:02:10 +08:00
*
* The idea is the following:
pkt_sched: Kill qdisc_lock_tree and qdisc_unlock_tree. No longer used. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 18:22:39 +08:00
* - enqueue, dequeue are serialized via qdisc root lock
* - ingress filtering is also serialized via qdisc root lock
[NET_SCHED]: Eliminate qdisc_tree_lock Since we're now holding the rtnl during the entire dump operation, we can remove qdisc_tree_lock, whose only purpose is to protect dump callbacks from concurrent changes to the qdisc tree. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-17 08:02:10 +08:00
* - updates to tree and tree walking are only done under the rtnl mutex.
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
*/
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
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);
net: sched: put back q.qlen into a single location In the series fc8b81a5981f ("Merge branch 'lockless-qdisc-series'") John made the assumption that the data path had no need to read the qdisc qlen (number of packets in the qdisc). It is true when pfifo_fast is used as the root qdisc, or as direct MQ/MQPRIO children. But pfifo_fast can be used as leaf in class full qdiscs, and existing logic needs to access the child qlen in an efficient way. HTB breaks badly, since it uses cl->leaf.q->q.qlen in : htb_activate() -> WARN_ON() htb_dequeue_tree() to decide if a class can be htb_deactivated when it has no more packets. HFSC, DRR, CBQ, QFQ have similar issues, and some calls to qdisc_tree_reduce_backlog() also read q.qlen directly. Using qdisc_qlen_sum() (which iterates over all possible cpus) in the data path is a non starter. It seems we have to put back qlen in a central location, at least for stable kernels. For all qdisc but pfifo_fast, qlen is guarded by the qdisc lock, so the existing q.qlen{++|--} are correct. For 'lockless' qdisc (pfifo_fast so far), we need to use atomic_{inc|dec}() because the spinlock might be not held (for example from pfifo_fast_enqueue() and pfifo_fast_dequeue()) This patch adds atomic_qlen (in the same location than qlen) and renames the following helpers, since we want to express they can be used without qdisc lock, and that qlen is no longer percpu. - qdisc_qstats_cpu_qlen_dec -> qdisc_qstats_atomic_qlen_dec() - qdisc_qstats_cpu_qlen_inc -> qdisc_qstats_atomic_qlen_inc() Later (net-next) we might revert this patch by tracking all these qlen uses and replace them by a more efficient method (not having to access a precise qlen, but an empty/non_empty status that might be less expensive to maintain/track). Another possibility is to have a legacy pfifo_fast version that would be used when used a a child qdisc, since the parent qdisc needs a spinlock anyway. But then, future lockless qdiscs would also have the same problem. Fixes: 7e66016f2c65 ("net: sched: helpers to sum qlen and qlen for per cpu logic") Signed-off-by: Eric Dumazet <edumazet@google.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> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-01 04:55:43 +08:00
qdisc_qstats_atomic_qlen_dec(q);
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
}
} else {
skb = NULL;
}
}
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 09:53:00 +08:00
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_inc(q, skb);
net: sched: put back q.qlen into a single location In the series fc8b81a5981f ("Merge branch 'lockless-qdisc-series'") John made the assumption that the data path had no need to read the qdisc qlen (number of packets in the qdisc). It is true when pfifo_fast is used as the root qdisc, or as direct MQ/MQPRIO children. But pfifo_fast can be used as leaf in class full qdiscs, and existing logic needs to access the child qlen in an efficient way. HTB breaks badly, since it uses cl->leaf.q->q.qlen in : htb_activate() -> WARN_ON() htb_dequeue_tree() to decide if a class can be htb_deactivated when it has no more packets. HFSC, DRR, CBQ, QFQ have similar issues, and some calls to qdisc_tree_reduce_backlog() also read q.qlen directly. Using qdisc_qlen_sum() (which iterates over all possible cpus) in the data path is a non starter. It seems we have to put back qlen in a central location, at least for stable kernels. For all qdisc but pfifo_fast, qlen is guarded by the qdisc lock, so the existing q.qlen{++|--} are correct. For 'lockless' qdisc (pfifo_fast so far), we need to use atomic_{inc|dec}() because the spinlock might be not held (for example from pfifo_fast_enqueue() and pfifo_fast_dequeue()) This patch adds atomic_qlen (in the same location than qlen) and renames the following helpers, since we want to express they can be used without qdisc lock, and that qlen is no longer percpu. - qdisc_qstats_cpu_qlen_dec -> qdisc_qstats_atomic_qlen_dec() - qdisc_qstats_cpu_qlen_inc -> qdisc_qstats_atomic_qlen_inc() Later (net-next) we might revert this patch by tracking all these qlen uses and replace them by a more efficient method (not having to access a precise qlen, but an empty/non_empty status that might be less expensive to maintain/track). Another possibility is to have a legacy pfifo_fast version that would be used when used a a child qdisc, since the parent qdisc needs a spinlock anyway. But then, future lockless qdiscs would also have the same problem. Fixes: 7e66016f2c65 ("net: sched: helpers to sum qlen and qlen for per cpu logic") Signed-off-by: Eric Dumazet <edumazet@google.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> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-01 04:55:43 +08:00
qdisc_qstats_atomic_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 09:53:00 +08:00
} else {
qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++;
}
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
if (lock)
spin_unlock(lock);
}
net: sched: always do stats accounting according to TCQ_F_CPUSTATS The core sched implementation checks independently for NOLOCK flag to acquire/release the root spin lock and for qdisc_is_percpu_stats() to account per CPU values in many places. This change update the last few places checking the TCQ_F_NOLOCK to do per CPU stats accounting according to qdisc_is_percpu_stats() value. The above allows to clean dev_requeue_skb() implementation a bit and makes stats update always consistent with a single flag. v1 -> v2: - do not move qdisc_is_empty definition, fix build issue Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-10 20:32:39 +08:00
static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
{
net: sched: always do stats accounting according to TCQ_F_CPUSTATS The core sched implementation checks independently for NOLOCK flag to acquire/release the root spin lock and for qdisc_is_percpu_stats() to account per CPU values in many places. This change update the last few places checking the TCQ_F_NOLOCK to do per CPU stats accounting according to qdisc_is_percpu_stats() value. The above allows to clean dev_requeue_skb() implementation a bit and makes stats update always consistent with a single flag. v1 -> v2: - do not move qdisc_is_empty definition, fix build issue Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-10 20:32:39 +08:00
spinlock_t *lock = NULL;
net: sched: fix skb leak in dev_requeue_skb() When dev_requeue_skb() is called with bulked skb list, only the first skb of the list will be requeued to qdisc layer, and leak the others without free them. TCP is broken due to skb leak since no free skb will be considered as still in the host queue and never be retransmitted. This happend when dev_requeue_skb() called from qdisc_restart(). qdisc_restart |-- dequeue_skb |-- sch_direct_xmit() |-- dev_requeue_skb() <-- skb may bluked Fix dev_requeue_skb() to requeue the full bluked list. Also change to use __skb_queue_tail() in __dev_requeue_skb() to avoid skb out of order. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-27 17:05:52 +08:00
net: sched: always do stats accounting according to TCQ_F_CPUSTATS The core sched implementation checks independently for NOLOCK flag to acquire/release the root spin lock and for qdisc_is_percpu_stats() to account per CPU values in many places. This change update the last few places checking the TCQ_F_NOLOCK to do per CPU stats accounting according to qdisc_is_percpu_stats() value. The above allows to clean dev_requeue_skb() implementation a bit and makes stats update always consistent with a single flag. v1 -> v2: - do not move qdisc_is_empty definition, fix build issue Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-10 20:32:39 +08:00
if (q->flags & TCQ_F_NOLOCK) {
lock = qdisc_lock(q);
spin_lock(lock);
net: sched: fix skb leak in dev_requeue_skb() When dev_requeue_skb() is called with bulked skb list, only the first skb of the list will be requeued to qdisc layer, and leak the others without free them. TCP is broken due to skb leak since no free skb will be considered as still in the host queue and never be retransmitted. This happend when dev_requeue_skb() called from qdisc_restart(). qdisc_restart |-- dequeue_skb |-- sch_direct_xmit() |-- dev_requeue_skb() <-- skb may bluked Fix dev_requeue_skb() to requeue the full bluked list. Also change to use __skb_queue_tail() in __dev_requeue_skb() to avoid skb out of order. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-27 17:05:52 +08:00
}
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
net: sched: fix skb leak in dev_requeue_skb() When dev_requeue_skb() is called with bulked skb list, only the first skb of the list will be requeued to qdisc layer, and leak the others without free them. TCP is broken due to skb leak since no free skb will be considered as still in the host queue and never be retransmitted. This happend when dev_requeue_skb() called from qdisc_restart(). qdisc_restart |-- dequeue_skb |-- sch_direct_xmit() |-- dev_requeue_skb() <-- skb may bluked Fix dev_requeue_skb() to requeue the full bluked list. Also change to use __skb_queue_tail() in __dev_requeue_skb() to avoid skb out of order. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-27 17:05:52 +08:00
while (skb) {
struct sk_buff *next = skb->next;
__skb_queue_tail(&q->gso_skb, skb);
net: sched: always do stats accounting according to TCQ_F_CPUSTATS The core sched implementation checks independently for NOLOCK flag to acquire/release the root spin lock and for qdisc_is_percpu_stats() to account per CPU values in many places. This change update the last few places checking the TCQ_F_NOLOCK to do per CPU stats accounting according to qdisc_is_percpu_stats() value. The above allows to clean dev_requeue_skb() implementation a bit and makes stats update always consistent with a single flag. v1 -> v2: - do not move qdisc_is_empty definition, fix build issue Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-10 20:32:39 +08:00
/* 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_atomic_qlen_inc(q);
} else {
q->qstats.requeues++;
qdisc_qstats_backlog_inc(q, skb);
q->q.qlen++;
}
net: sched: fix skb leak in dev_requeue_skb() When dev_requeue_skb() is called with bulked skb list, only the first skb of the list will be requeued to qdisc layer, and leak the others without free them. TCP is broken due to skb leak since no free skb will be considered as still in the host queue and never be retransmitted. This happend when dev_requeue_skb() called from qdisc_restart(). qdisc_restart |-- dequeue_skb |-- sch_direct_xmit() |-- dev_requeue_skb() <-- skb may bluked Fix dev_requeue_skb() to requeue the full bluked list. Also change to use __skb_queue_tail() in __dev_requeue_skb() to avoid skb out of order. Fixes: a53851e2c321 ("net: sched: explicit locking in gso_cpu fallback") Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-27 17:05:52 +08:00
skb = next;
}
net: sched: always do stats accounting according to TCQ_F_CPUSTATS The core sched implementation checks independently for NOLOCK flag to acquire/release the root spin lock and for qdisc_is_percpu_stats() to account per CPU values in many places. This change update the last few places checking the TCQ_F_NOLOCK to do per CPU stats accounting according to qdisc_is_percpu_stats() value. The above allows to clean dev_requeue_skb() implementation a bit and makes stats update always consistent with a single flag. v1 -> v2: - do not move qdisc_is_empty definition, fix build issue Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-10 20:32:39 +08:00
if (lock)
spin_unlock(lock);
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
__netif_schedule(q);
}
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
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 18:18:10 +08:00
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>
2014-10-02 04:35:59 +08:00
{
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
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>
2014-10-02 04:35:59 +08:00
while (bytelimit > 0) {
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
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>
2014-10-02 04:35:59 +08:00
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
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>
2014-10-02 04:35:59 +08:00
break;
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
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 18:18:10 +08:00
(*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>
2014-10-02 04:35:59 +08:00
}
net: Add and use skb_mark_not_on_list(). An SKB is not on a list if skb->next is NULL. Codify this convention into a helper function and use it where we are dequeueing an SKB and need to mark it as such. Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-30 11:42:53 +08:00
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>
2014-10-02 04:35:59 +08:00
}
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
/* 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)) {
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
qdisc_enqueue_skb_bad_txq(q, nskb);
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
break;
}
skb->next = nskb;
skb = nskb;
} while (++cnt < 8);
(*packets) += cnt;
net: Add and use skb_mark_not_on_list(). An SKB is not on a list if skb->next is NULL. Codify this convention into a helper function and use it where we are dequeueing an SKB and need to mark it as such. Signed-off-by: David S. Miller <davem@davemloft.net>
2018-07-30 11:42:53 +08:00
skb_mark_not_on_list(skb);
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
}
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>
2014-10-02 04:35:59 +08:00
/* 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 18:18:10 +08:00
static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
int *packets)
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
{
pkt_sched: avoid requeues if possible With BQL being deployed, we can more likely have following behavior : We dequeue a packet from qdisc in dequeue_skb(), then we realize target tx queue is in XOFF state in sch_direct_xmit(), and we have to hold the skb into gso_skb for later. This shows in stats (tc -s qdisc dev eth0) as requeues. Problem of these requeues is that high priority packets can not be dequeued as long as this (possibly low prio and big TSO packet) is not removed from gso_skb. At 1Gbps speed, a full size TSO packet is 500 us of extra latency. In some cases, we know that all packets dequeued from a qdisc are for a particular and known txq : - If device is non multi queue - For all MQ/MQPRIO slave qdiscs This patch introduces a new qdisc flag, TCQ_F_ONETXQUEUE to mark this capability, so that dequeue_skb() is allowed to dequeue a packet only if the associated txq is not stopped. This indeed reduce latencies for high prio packets (or improve fairness with sfq/fq_codel), and almost remove qdisc 'requeues'. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-12-11 23:54:33 +08:00
const struct netdev_queue *txq = q->dev_queue;
net: sched: check for frozen queue before skb_bad_txq check I can not think of any reason to pull the bad txq skb off the qdisc if the txq we plan to send this on is still frozen. So check for frozen queue first and abort before dequeuing either skb_bad_txq skb or normal qdisc dequeue() skb. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:42 +08:00
struct sk_buff *skb = NULL;
pkt_sched: Fix handling of gso skbs on requeuing Jay Cliburn noticed and diagnosed a bug triggered in dev_gso_skb_destructor() after last change from qdisc->gso_skb to qdisc->requeue list. Since gso_segmented skbs can't be queued to another list this patch brings back qdisc->gso_skb for them. Reported-by: Jay Cliburn <jcliburn@gmail.com> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-07 00:54:39 +08:00
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 18:18:10 +08:00
*packets = 1;
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
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;
}
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
/* skb in gso_skb were already validated */
*validate = false;
net: Add asynchronous callbacks for xfrm on layer 2. This patch implements asynchronous crypto callbacks and a backlog handler that can be used when IPsec is done at layer 2 in the TX path. It also extends the skb validate functions so that we can update the driver transmit return codes based on async crypto operation or to indicate that we queued the packet in a backlog queue. Joint work with: Aviv Heller <avivh@mellanox.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-12-20 17:41:36 +08:00
if (xfrm_offload(skb))
*validate = true;
pkt_sched: Check the state of tx_queue in dequeue_skb() Check in dequeue_skb() the state of tx_queue for requeued skb to save on locking and re-requeuing, and possibly remove the current check in qdisc_run(). Based on the idea of Alexander Duyck. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-23 13:16:23 +08:00
/* check the reason of requeuing without tx lock first */
net: add skb_get_tx_queue() helper Replace occurences of skb_get_queue_mapping() and follow-up netdev_get_tx_queue() with an actual helper function. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-27 17:11:27 +08:00
txq = skb_get_tx_queue(txq->dev, skb);
net: Add queue state xoff flag for stack Create separate queue state flags so that either the stack or drivers can turn on XOFF. Added a set of functions used in the stack to determine if a queue is really stopped (either by stack or driver) Signed-off-by: Tom Herbert <therbert@google.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-29 00:32:44 +08:00
if (!netif_xmit_frozen_or_stopped(txq)) {
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
skb = __skb_dequeue(&q->gso_skb);
if (qdisc_is_percpu_stats(q)) {
qdisc_qstats_cpu_backlog_dec(q, skb);
net: sched: put back q.qlen into a single location In the series fc8b81a5981f ("Merge branch 'lockless-qdisc-series'") John made the assumption that the data path had no need to read the qdisc qlen (number of packets in the qdisc). It is true when pfifo_fast is used as the root qdisc, or as direct MQ/MQPRIO children. But pfifo_fast can be used as leaf in class full qdiscs, and existing logic needs to access the child qlen in an efficient way. HTB breaks badly, since it uses cl->leaf.q->q.qlen in : htb_activate() -> WARN_ON() htb_dequeue_tree() to decide if a class can be htb_deactivated when it has no more packets. HFSC, DRR, CBQ, QFQ have similar issues, and some calls to qdisc_tree_reduce_backlog() also read q.qlen directly. Using qdisc_qlen_sum() (which iterates over all possible cpus) in the data path is a non starter. It seems we have to put back qlen in a central location, at least for stable kernels. For all qdisc but pfifo_fast, qlen is guarded by the qdisc lock, so the existing q.qlen{++|--} are correct. For 'lockless' qdisc (pfifo_fast so far), we need to use atomic_{inc|dec}() because the spinlock might be not held (for example from pfifo_fast_enqueue() and pfifo_fast_dequeue()) This patch adds atomic_qlen (in the same location than qlen) and renames the following helpers, since we want to express they can be used without qdisc lock, and that qlen is no longer percpu. - qdisc_qstats_cpu_qlen_dec -> qdisc_qstats_atomic_qlen_dec() - qdisc_qstats_cpu_qlen_inc -> qdisc_qstats_atomic_qlen_inc() Later (net-next) we might revert this patch by tracking all these qlen uses and replace them by a more efficient method (not having to access a precise qlen, but an empty/non_empty status that might be less expensive to maintain/track). Another possibility is to have a legacy pfifo_fast version that would be used when used a a child qdisc, since the parent qdisc needs a spinlock anyway. But then, future lockless qdiscs would also have the same problem. Fixes: 7e66016f2c65 ("net: sched: helpers to sum qlen and qlen for per cpu logic") Signed-off-by: Eric Dumazet <edumazet@google.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> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-01 04:55:43 +08:00
qdisc_qstats_atomic_qlen_dec(q);
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
} else {
qdisc_qstats_backlog_dec(q, skb);
q->q.qlen--;
}
} else {
pkt_sched: Check the state of tx_queue in dequeue_skb() Check in dequeue_skb() the state of tx_queue for requeued skb to save on locking and re-requeuing, and possibly remove the current check in qdisc_run(). Based on the idea of Alexander Duyck. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-23 13:16:23 +08:00
skb = NULL;
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
}
if (lock)
spin_unlock(lock);
qdisc: add tracepoint qdisc:qdisc_dequeue for dequeued SKBs The main purpose of this tracepoint is to monitor bulk dequeue in the network qdisc layer, as it cannot be deducted from the existing qdisc stats. The txq_state can be used for determining the reason for zero packet dequeues, see enum netdev_queue_state_t. Notice all packets doesn't necessary activate this tracepoint. As qdiscs with flag TCQ_F_CAN_BYPASS, can directly invoke sch_direct_xmit() when qdisc_qlen is zero. Remember that perf record supports filters like: perf record -e qdisc:qdisc_dequeue \ --filter 'ifindex == 4 && (packets > 1 || txq_state > 0)' Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 03:11:03 +08:00
goto trace;
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
}
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
validate:
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
*validate = true;
net: sched: check for frozen queue before skb_bad_txq check I can not think of any reason to pull the bad txq skb off the qdisc if the txq we plan to send this on is still frozen. So check for frozen queue first and abort before dequeuing either skb_bad_txq skb or normal qdisc dequeue() skb. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:42 +08:00
if ((q->flags & TCQ_F_ONETXQUEUE) &&
netif_xmit_frozen_or_stopped(txq))
return skb;
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
skb = qdisc_dequeue_skb_bad_txq(q);
if (unlikely(skb))
goto bulk;
net: sched: check for frozen queue before skb_bad_txq check I can not think of any reason to pull the bad txq skb off the qdisc if the txq we plan to send this on is still frozen. So check for frozen queue first and abort before dequeuing either skb_bad_txq skb or normal qdisc dequeue() skb. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:42 +08:00
skb = q->dequeue(q);
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
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);
pkt_sched: Check the state of tx_queue in dequeue_skb() Check in dequeue_skb() the state of tx_queue for requeued skb to save on locking and re-requeuing, and possibly remove the current check in qdisc_run(). Based on the idea of Alexander Duyck. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-23 13:16:23 +08:00
}
qdisc: add tracepoint qdisc:qdisc_dequeue for dequeued SKBs The main purpose of this tracepoint is to monitor bulk dequeue in the network qdisc layer, as it cannot be deducted from the existing qdisc stats. The txq_state can be used for determining the reason for zero packet dequeues, see enum netdev_queue_state_t. Notice all packets doesn't necessary activate this tracepoint. As qdiscs with flag TCQ_F_CAN_BYPASS, can directly invoke sch_direct_xmit() when qdisc_qlen is zero. Remember that perf record supports filters like: perf record -e qdisc:qdisc_dequeue \ --filter 'ifindex == 4 && (packets > 1 || txq_state > 0)' Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-16 03:11:03 +08:00
trace:
trace_qdisc_dequeue(q, txq, *packets, skb);
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
return skb;
}
[NET] SCHED: Fix whitespace errors. Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-09 22:25:16 +08:00
/*
qdisc: adjustments for API allowing skb list xmits Minor adjustments for merge commit 53fda7f7f9e (Merge branch 'xmit_list') that allows us to work with a list of SKBs. Update code doc to function sch_direct_xmit(). In handle_dev_cpu_collision() use kfree_skb_list() in error handling. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-02 22:35:33 +08:00
* Transmit possibly several skbs, and handle the return status as
net_sched: transform qdisc running bit into a seqcount Instead of using a single bit (__QDISC___STATE_RUNNING) in sch->__state, use a seqcount. This adds lockdep support, but more importantly it will allow us to sample qdisc/class statistics without having to grab qdisc root lock. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-07 00:37:15 +08:00
* required. Owning running seqcount bit guarantees that
qdisc: adjustments for API allowing skb list xmits Minor adjustments for merge commit 53fda7f7f9e (Merge branch 'xmit_list') that allows us to work with a list of SKBs. Update code doc to function sch_direct_xmit(). In handle_dev_cpu_collision() use kfree_skb_list() in error handling. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-02 22:35:33 +08:00
* 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 10:56:09 +08:00
*
* Returns to the caller:
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
* 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 10:56:09 +08:00
*/
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
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)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
[PKT_SCHED]: Check subqueue status before calling hard_start_xmit The only qdiscs that check subqueue state before dequeue'ing are PRIO and RR. The other qdiscs, including the default pfifo_fast qdisc, will allow traffic bound for subqueue 0 through to hard_start_xmit. The check for netif_queue_stopped() is done above in pkt_sched.h, so it is unnecessary for qdisc_restart(). However, if the underlying driver is multiqueue capable, and only sets queue states on subqueues, this will allow packets to enter the driver when it's currently unable to process packets, resulting in expensive requeues and driver entries. This patch re-adds the check for the subqueue status before calling hard_start_xmit, so we can try and avoid the driver entry when the queues are stopped. Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-14 12:40:55 +08:00
int ret = NETDEV_TX_BUSY;
net: Add asynchronous callbacks for xfrm on layer 2. This patch implements asynchronous crypto callbacks and a backlog handler that can be used when IPsec is done at layer 2 in the TX path. It also extends the skb validate functions so that we can update the driver transmit return codes based on async crypto operation or to indicate that we queued the packet in a backlog queue. Joint work with: Aviv Heller <avivh@mellanox.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-12-20 17:41:36 +08:00
bool again = false;
pkt_sched: Add and use qdisc_root() and qdisc_root_lock(). When code wants to lock the qdisc tree state, the logic operation it's doing is locking the top-level qdisc that sits of the root of the netdev_queue. Add qdisc_root_lock() to represent this and convert the easiest cases. In order for this to work out in all cases, we have to hook up the noop_qdisc to a dummy netdev_queue. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 16:42:40 +08:00
/* And release qdisc */
net: sched: allow qdiscs to handle locking This patch adds a flag for queueing disciplines to indicate the stack does not need to use the qdisc lock to protect operations. This can be used to build lockless scheduling algorithms and improving performance. The flag is checked in the tx path and the qdisc lock is only taken if it is not set. For now use a conditional if statement. Later we could be more aggressive if it proves worthwhile and use a static key or wrap this in a likely(). Also the lockless case drops the TCQ_F_CAN_BYPASS logic. The reason for this is synchronizing a qlen counter across threads proves to cost more than doing the enqueue/dequeue operations when tested with pktgen. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:25 +08:00
if (root_lock)
spin_unlock(root_lock);
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
/* Note that we validate skb (GSO, checksum, ...) outside of locks */
if (validate)
net: Add asynchronous callbacks for xfrm on layer 2. This patch implements asynchronous crypto callbacks and a backlog handler that can be used when IPsec is done at layer 2 in the TX path. It also extends the skb validate functions so that we can update the driver transmit return codes based on async crypto operation or to indicate that we queued the packet in a backlog queue. Joint work with: Aviv Heller <avivh@mellanox.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
2017-12-20 17:41:36 +08:00
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
net: allow to propagate errors through ->ndo_hard_start_xmit() Currently the ->ndo_hard_start_xmit() callbacks are only permitted to return one of the NETDEV_TX codes. This prevents any kind of error propagation for virtual devices, like queue congestion of the underlying device in case of layered devices, or unreachability in case of tunnels. This patches changes the NET_XMIT codes to avoid clashes with the NETDEV_TX codes and changes the two callers of dev_hard_start_xmit() to expect either errno codes, NET_XMIT codes or NETDEV_TX codes as return value. In case of qdisc_restart(), all non NETDEV_TX codes are mapped to NETDEV_TX_OK since no error propagation is possible when using qdiscs. In case of dev_queue_xmit(), the error is propagated upwards. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-11-10 14:14:14 +08:00
net: sched: do not requeue a NULL skb A failure in validate_xmit_skb_list() triggered an unconditional call to dev_requeue_skb with skb=NULL. This slowly grows the queue discipline's qlen count until all traffic through the queue stops. We take the optimistic approach and continue running the queue after a failure since it is unknown if later packets also will fail in the validate path. Fixes: 55a93b3ea780 ("qdisc: validate skb without holding lock") Signed-off-by: Lars Persson <larper@axis.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-12 14:45:52 +08:00
if (likely(skb)) {
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
skb = dev_hard_start_xmit(skb, dev, txq, &ret);
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
HARD_TX_UNLOCK(dev, txq);
net: sched: do not requeue a NULL skb A failure in validate_xmit_skb_list() triggered an unconditional call to dev_requeue_skb with skb=NULL. This slowly grows the queue discipline's qlen count until all traffic through the queue stops. We take the optimistic approach and continue running the queue after a failure since it is unknown if later packets also will fail in the validate path. Fixes: 55a93b3ea780 ("qdisc: validate skb without holding lock") Signed-off-by: Lars Persson <larper@axis.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-12 14:45:52 +08:00
} else {
net: sched: allow qdiscs to handle locking This patch adds a flag for queueing disciplines to indicate the stack does not need to use the qdisc lock to protect operations. This can be used to build lockless scheduling algorithms and improving performance. The flag is checked in the tx path and the qdisc lock is only taken if it is not set. For now use a conditional if statement. Later we could be more aggressive if it proves worthwhile and use a static key or wrap this in a likely(). Also the lockless case drops the TCQ_F_CAN_BYPASS logic. The reason for this is synchronizing a qlen counter across threads proves to cost more than doing the enqueue/dequeue operations when tested with pktgen. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:25 +08:00
if (root_lock)
spin_lock(root_lock);
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
return true;
qdisc: validate skb without holding lock Validation of skb can be pretty expensive : GSO segmentation and/or checksum computations. We can do this without holding qdisc lock, so that other cpus can queue additional packets. Trick is that requeued packets were already validated, so we carry a boolean so that sch_direct_xmit() can validate a fresh skb list, or directly use an old one. Tested on 40Gb NIC (8 TX queues) and 200 concurrent flows, 48 threads host. Turning TSO on or off had no effect on throughput, only few more cpu cycles. Lock contention on qdisc lock disappeared. Same if disabling TX checksum offload. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-10-04 06:31:07 +08:00
}
net: sched: allow qdiscs to handle locking This patch adds a flag for queueing disciplines to indicate the stack does not need to use the qdisc lock to protect operations. This can be used to build lockless scheduling algorithms and improving performance. The flag is checked in the tx path and the qdisc lock is only taken if it is not set. For now use a conditional if statement. Later we could be more aggressive if it proves worthwhile and use a static key or wrap this in a likely(). Also the lockless case drops the TCQ_F_CAN_BYPASS logic. The reason for this is synchronizing a qlen counter across threads proves to cost more than doing the enqueue/dequeue operations when tested with pktgen. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:25 +08:00
if (root_lock)
spin_lock(root_lock);
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
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 10:56:09 +08:00
/* Driver returned NETDEV_TX_BUSY - requeue skb */
net: Convert net_ratelimit uses to net_<level>_ratelimited Standardize the net core ratelimited logging functions. Coalesce formats, align arguments. Change a printk then vprintk sequence to use printf extension %pV. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-05-14 05:56:26 +08:00
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 10:56:09 +08:00
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
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 10:56:09 +08:00
}
[NET_SCHED]: Cleanup readability of qdisc restart Over the years this code has gotten hairier. Resulting in many long discussions over long summer days and patches that get it wrong. This patch helps tame that code so normal people will understand it. Thanks to Thomas Graf, Peter J. waskiewicz Jr, and Patrick McHardy for their valuable reviews. Signed-off-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-11 08:31:24 +08:00
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
return true;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
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 09:44:21 +08:00
/*
* NOTE: Called under qdisc_lock(q) with locally disabled BH.
*
net_sched: transform qdisc running bit into a seqcount Instead of using a single bit (__QDISC___STATE_RUNNING) in sch->__state, use a seqcount. This adds lockdep support, but more importantly it will allow us to sample qdisc/class statistics without having to grab qdisc root lock. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-07 00:37:15 +08:00
* 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 09:44:21 +08:00
* 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.
*
*/
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
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 09:44:21 +08:00
{
net: sched: allow qdiscs to handle locking This patch adds a flag for queueing disciplines to indicate the stack does not need to use the qdisc lock to protect operations. This can be used to build lockless scheduling algorithms and improving performance. The flag is checked in the tx path and the qdisc lock is only taken if it is not set. For now use a conditional if statement. Later we could be more aggressive if it proves worthwhile and use a static key or wrap this in a likely(). Also the lockless case drops the TCQ_F_CAN_BYPASS logic. The reason for this is synchronizing a qlen counter across threads proves to cost more than doing the enqueue/dequeue operations when tested with pktgen. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:25 +08:00
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 09:44:21 +08:00
struct netdev_queue *txq;
struct net_device *dev;
struct sk_buff *skb;
sched: manipulate __QDISC_STATE_RUNNING in qdisc_run_* helpers Currently NOLOCK qdiscs pay a measurable overhead to atomically manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per packet in the uncontended scenario with packet rate below the line rate: on packed dequeue and on the next, failing dequeue attempt. This changeset moves the bit manipulation into the qdisc_run_{begin,end} helpers, so that the bit is now flipped only once per packet, with measurable performance improvement in the uncontended scenario. This also allows simplifying the qdisc teardown code path - since qdisc_is_running() is now effective for each qdisc type - and avoid a possible race between qdisc_run() and dev_deactivate_many(), as now the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy dequeuing packets. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 16:50:31 +08:00
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 09:44:21 +08:00
/* 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 18:18:10 +08:00
skb = dequeue_skb(q, &validate, packets);
sched: manipulate __QDISC_STATE_RUNNING in qdisc_run_* helpers Currently NOLOCK qdiscs pay a measurable overhead to atomically manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per packet in the uncontended scenario with packet rate below the line rate: on packed dequeue and on the next, failing dequeue attempt. This changeset moves the bit manipulation into the qdisc_run_{begin,end} helpers, so that the bit is now flipped only once per packet, with measurable performance improvement in the uncontended scenario. This also allows simplifying the qdisc teardown code path - since qdisc_is_running() is now effective for each qdisc type - and avoid a possible race between qdisc_run() and dev_deactivate_many(), as now the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy dequeuing packets. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 16:50:31 +08:00
if (unlikely(!skb))
net: sched: remove remaining uses for qdisc_qlen in xmit path sch_direct_xmit() uses qdisc_qlen as a return value but all call sites of the routine only check if it is zero or not. Simplify the logic so that we don't need to return an actual queue length value. This introduces a case now where sch_direct_xmit would have returned a qlen of zero but now it returns true. However in this case all call sites of sch_direct_xmit will implement a dequeue() and get a null skb and abort. This trades tracking qlen in the hotpath for an extra dequeue operation. Overall this seems to be good for performance. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:47 +08:00
return false;
net: add skb_get_tx_queue() helper Replace occurences of skb_get_queue_mapping() and follow-up netdev_get_tx_queue() with an actual helper function. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-27 17:11:27 +08:00
sched: manipulate __QDISC_STATE_RUNNING in qdisc_run_* helpers Currently NOLOCK qdiscs pay a measurable overhead to atomically manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per packet in the uncontended scenario with packet rate below the line rate: on packed dequeue and on the next, failing dequeue attempt. This changeset moves the bit manipulation into the qdisc_run_{begin,end} helpers, so that the bit is now flipped only once per packet, with measurable performance improvement in the uncontended scenario. This also allows simplifying the qdisc teardown code path - since qdisc_is_running() is now effective for each qdisc type - and avoid a possible race between qdisc_run() and dev_deactivate_many(), as now the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy dequeuing packets. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 16:50:31 +08:00
if (!(q->flags & TCQ_F_NOLOCK))
net: sched: allow qdiscs to handle locking This patch adds a flag for queueing disciplines to indicate the stack does not need to use the qdisc lock to protect operations. This can be used to build lockless scheduling algorithms and improving performance. The flag is checked in the tx path and the qdisc lock is only taken if it is not set. For now use a conditional if statement. Later we could be more aggressive if it proves worthwhile and use a static key or wrap this in a likely(). Also the lockless case drops the TCQ_F_CAN_BYPASS logic. The reason for this is synchronizing a qlen counter across threads proves to cost more than doing the enqueue/dequeue operations when tested with pktgen. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:54:25 +08:00
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 09:44:21 +08:00
dev = qdisc_dev(q);
net: add skb_get_tx_queue() helper Replace occurences of skb_get_queue_mapping() and follow-up netdev_get_tx_queue() with an actual helper function. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-08-27 17:11:27 +08:00
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 09:44:21 +08:00
sched: manipulate __QDISC_STATE_RUNNING in qdisc_run_* helpers Currently NOLOCK qdiscs pay a measurable overhead to atomically manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per packet in the uncontended scenario with packet rate below the line rate: on packed dequeue and on the next, failing dequeue attempt. This changeset moves the bit manipulation into the qdisc_run_{begin,end} helpers, so that the bit is now flipped only once per packet, with measurable performance improvement in the uncontended scenario. This also allows simplifying the qdisc teardown code path - since qdisc_is_running() is now effective for each qdisc type - and avoid a possible race between qdisc_run() and dev_deactivate_many(), as now the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy dequeuing packets. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 16:50:31 +08:00
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 09:44:21 +08:00
}
pkt_sched: Schedule qdiscs instead of netdev_queue. When we have shared qdiscs, packets come out of the qdiscs for multiple transmit queues. Therefore it doesn't make any sense to schedule the transmit queue when logically we cannot know ahead of time the TX queue of the SKB that the qdisc->dequeue() will give us. Just for sanity I added a BUG check to make sure we never get into a state where the noop_qdisc is scheduled. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 17:15:04 +08:00
void __qdisc_run(struct Qdisc *q)
[NET]: Prevent multiple qdisc runs Having two or more qdisc_run's contend against each other is bad because it can induce packet reordering if the packets have to be requeued. It appears that this is an unintended consequence of relinquinshing the queue lock while transmitting. That in turn is needed for devices that spend a lot of time in their transmit routine. There are no advantages to be had as devices with queues are inherently single-threaded (the loopback device is not but then it doesn't have a queue). Even if you were to add a queue to a parallel virtual device (e.g., bolt a tbf filter in front of an ipip tunnel device), you would still want to process the queue in sequence to ensure that the packets are ordered correctly. The solution here is to steal a bit from net_device to prevent this. BTW, as qdisc_restart is no longer used by anyone as a module inside the kernel (IIRC it used to with netif_wake_queue), I have not exported the new __qdisc_run function. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-20 14:57:59 +08:00
{
net: dev_weight: TX/RX orthogonality Oftenly, introducing side effects on packet processing on the other half of the stack by adjusting one of TX/RX via sysctl is not desirable. There are cases of demand for asymmetric, orthogonal configurability. This holds true especially for nodes where RPS for RFS usage on top is configured and therefore use the 'old dev_weight'. This is quite a common base configuration setup nowadays, even with NICs of superior processing support (e.g. aRFS). A good example use case are nodes acting as noSQL data bases with a large number of tiny requests and rather fewer but large packets as responses. It's affordable to have large budget and rx dev_weights for the requests. But as a side effect having this large a number on TX processed in one run can overwhelm drivers. This patch therefore introduces an independent configurability via sysctl to userland. Signed-off-by: Matthias Tafelmeier <matthias.tafelmeier@gmx.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-30 04:37:21 +08:00
int quota = 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 18:18:10 +08:00
int packets;
[NET]: Add preemption point in qdisc_run The qdisc_run loop is currently unbounded and runs entirely in a softirq. This is bad as it may create an unbounded softirq run. This patch fixes this by calling need_resched and breaking out if necessary. It also adds a break out if the jiffies value changes since that would indicate we've been transmitting for too long which starves other softirqs. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-29 07:25:26 +08:00
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 18:18:10 +08:00
while (qdisc_restart(q, &packets)) {
[NET]: Add preemption point in qdisc_run The qdisc_run loop is currently unbounded and runs entirely in a softirq. This is bad as it may create an unbounded softirq run. This patch fixes this by calling need_resched and breaking out if necessary. It also adds a break out if the jiffies value changes since that would indicate we've been transmitting for too long which starves other softirqs. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-29 07:25:26 +08:00
/*
net_sched: fix dequeuer fairness Results on dummy device can be seen in my netconf 2011 slides. These results are for a 10Gige IXGBE intel nic - on another i5 machine, very similar specs to the one used in the netconf2011 results. It turns out - this is a hell lot worse than dummy and so this patch is even more beneficial for 10G. Test setup: ---------- System under test sending packets out. Additional box connected directly dropping packets. Installed prio qdisc on the eth device and default netdev default length of 1000 used as is. The 3 prio bands each were set to 100 (didnt factor in the results). 5 packet runs were made and the middle 3 picked. results ------- The "cpu" column indicates the which cpu the sample was taken on, The "Pkt runx" carries the number of packets a cpu dequeued when forced to be in the "dequeuer" role. The "avg" for each run is the number of times each cpu should be a "dequeuer" if the system was fair. 3.0-rc4 (plain) cpu Pkt run1 Pkt run2 Pkt run3 ================================================ cpu0 21853354 21598183 22199900 cpu1 431058 473476 393159 cpu2 481975 477529 458466 cpu3 23261406 23412299 22894315 avg 11506948 11490372 11486460 3.0-rc4 with patch and default weight 64 cpu Pkt run1 Pkt run2 Pkt run3 ================================================ cpu0 13205312 13109359 13132333 cpu1 10189914 10159127 10122270 cpu2 10213871 10124367 10168722 cpu3 13165760 13164767 13096705 avg 11693714 11639405 11630008 As you can see the system is still not perfect but is a lot better than what it was before... At the moment we use the old backlog weight, weight_p which is 64 packets. It seems to be reasonably fine with that value. The system could be made more fair if we reduce the weight_p (as per my presentation), but we are going to affect the shared backlog weight. Unless deemed necessary, I think the default value is fine. If not we could add yet another knob. Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-06-26 16:13:54 +08:00
* Ordered by possible occurrence: Postpone processing if
* 1. we've exceeded packet quota
* 2. another process needs the CPU;
[NET]: Add preemption point in qdisc_run The qdisc_run loop is currently unbounded and runs entirely in a softirq. This is bad as it may create an unbounded softirq run. This patch fixes this by calling need_resched and breaking out if necessary. It also adds a break out if the jiffies value changes since that would indicate we've been transmitting for too long which starves other softirqs. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-29 07:25:26 +08:00
*/
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 18:18:10 +08:00
quota -= packets;
if (quota <= 0 || need_resched()) {
pkt_sched: Schedule qdiscs instead of netdev_queue. When we have shared qdiscs, packets come out of the qdiscs for multiple transmit queues. Therefore it doesn't make any sense to schedule the transmit queue when logically we cannot know ahead of time the TX queue of the SKB that the qdisc->dequeue() will give us. Just for sanity I added a BUG check to make sure we never get into a state where the noop_qdisc is scheduled. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 17:15:04 +08:00
__netif_schedule(q);
[NET_SCHED]: Rationalise return value of qdisc_restart The current return value scheme and associated comment was invented back in the 20th century when we still had that tbusy flag. Things have changed quite a bit since then (even Tony Blair is moving on now, not to mention the new French president). All we need to indicate now is whether the caller should continue processing the queue. Therefore it's sufficient if we return 0 if we want to stop and non-zero otherwise. This is based on a patch by Krishna Kumar. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-10 19:55:14 +08:00
break;
[NET]: Add preemption point in qdisc_run The qdisc_run loop is currently unbounded and runs entirely in a softirq. This is bad as it may create an unbounded softirq run. This patch fixes this by calling need_resched and breaking out if necessary. It also adds a break out if the jiffies value changes since that would indicate we've been transmitting for too long which starves other softirqs. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-29 07:25:26 +08:00
}
}
[NET]: Prevent multiple qdisc runs Having two or more qdisc_run's contend against each other is bad because it can induce packet reordering if the packets have to be requeued. It appears that this is an unintended consequence of relinquinshing the queue lock while transmitting. That in turn is needed for devices that spend a lot of time in their transmit routine. There are no advantages to be had as devices with queues are inherently single-threaded (the loopback device is not but then it doesn't have a queue). Even if you were to add a queue to a parallel virtual device (e.g., bolt a tbf filter in front of an ipip tunnel device), you would still want to process the queue in sequence to ensure that the packets are ordered correctly. The solution here is to steal a bit from net_device to prevent this. BTW, as qdisc_restart is no longer used by anyone as a module inside the kernel (IIRC it used to with netif_wake_queue), I have not exported the new __qdisc_run function. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-20 14:57:59 +08:00
}
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
unsigned long dev_trans_start(struct net_device *dev)
{
net_sched: make dev_trans_start return vlan's real dev trans_start Vlan devices are LLTX and don't update their own trans_start, so if dev_trans_start has to be called with a vlan device then 0 or a stale value will be returned. Currently the bonding is the only such user, and it's needed for proper arp monitoring when the slaves are vlans. Fix this by extracting the vlan's real device trans_start. Suggested-by: David Miller <davem@davemloft.net> Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Acked-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-04 04:07:47 +08:00
unsigned long val, res;
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
unsigned int i;
net_sched: make dev_trans_start return vlan's real dev trans_start Vlan devices are LLTX and don't update their own trans_start, so if dev_trans_start has to be called with a vlan device then 0 or a stale value will be returned. Currently the bonding is the only such user, and it's needed for proper arp monitoring when the slaves are vlans. Fix this by extracting the vlan's real device trans_start. Suggested-by: David Miller <davem@davemloft.net> Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Acked-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-04 04:07:47 +08:00
if (is_vlan_dev(dev))
dev = vlan_dev_real_dev(dev);
net_sched: use macvlan real dev trans_start in dev_trans_start() Macvlan devices are similar to vlans and do not update their own trans_start. In order for arp monitoring to work for a bond device when the slaves are macvlans, obtain its real device. Signed-off-by: Chris Dion <christopher.dion@dell.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-06 23:50:28 +08:00
else if (netif_is_macvlan(dev))
dev = macvlan_dev_real_dev(dev);
net: remove dev->trans_start previous patches removed all direct accesses to dev->trans_start, so change the netif_trans_update helper to update trans_start of netdev queue 0 instead and then remove trans_start from struct net_device. AFAICS a lot of the netif_trans_update() invocations are now useless because they occur in ndo_start_xmit and driver doesn't set LLTX (i.e. stack already took care of the update). As I can't test any of them it seems better to just leave them alone. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-03 22:33:14 +08:00
res = netdev_get_tx_queue(dev, 0)->trans_start;
for (i = 1; i < dev->num_tx_queues; i++) {
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
val = netdev_get_tx_queue(dev, i)->trans_start;
if (val && time_after(val, res))
res = val;
}
net_sched: make dev_trans_start return vlan's real dev trans_start Vlan devices are LLTX and don't update their own trans_start, so if dev_trans_start has to be called with a vlan device then 0 or a stale value will be returned. Currently the bonding is the only such user, and it's needed for proper arp monitoring when the slaves are vlans. Fix this by extracting the vlan's real device trans_start. Suggested-by: David Miller <davem@davemloft.net> Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com> Acked-by: Veaceslav Falico <vfalico@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-04 04:07:47 +08:00
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
return res;
}
EXPORT_SYMBOL(dev_trans_start);
net: sched: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Add pointer back to Qdisc. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-17 08:29:17 +08:00
static void dev_watchdog(struct timer_list *t)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
net: sched: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Add pointer back to Qdisc. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-17 08:29:17 +08:00
struct net_device *dev = from_timer(dev, t, watchdog_timer);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[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>
2006-06-10 03:20:56 +08:00
netif_tx_lock(dev);
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
if (!qdisc_tx_is_noop(dev)) {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (netif_device_present(dev) &&
netif_running(dev) &&
netif_carrier_ok(dev)) {
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
int some_queue_timedout = 0;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
unsigned int i;
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
unsigned long trans_start;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq;
txq = netdev_get_tx_queue(dev, i);
net: remove dev->trans_start previous patches removed all direct accesses to dev->trans_start, so change the netif_trans_update helper to update trans_start of netdev queue 0 instead and then remove trans_start from struct net_device. AFAICS a lot of the netif_trans_update() invocations are now useless because they occur in ndo_start_xmit and driver doesn't set LLTX (i.e. stack already took care of the update). As I can't test any of them it seems better to just leave them alone. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-03 22:33:14 +08:00
trans_start = txq->trans_start;
net: Add queue state xoff flag for stack Create separate queue state flags so that either the stack or drivers can turn on XOFF. Added a set of functions used in the stack to determine if a queue is really stopped (either by stack or driver) Signed-off-by: Tom Herbert <therbert@google.com> Acked-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-29 00:32:44 +08:00
if (netif_xmit_stopped(txq) &&
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
time_after(jiffies, (trans_start +
dev->watchdog_timeo))) {
some_queue_timedout = 1;
net: new counter for tx_timeout errors in sysfs This adds the /sys/class/net/DEV/queues/Q/tx_timeout attribute containing the total number of timeout events on the given queue. It is always available with CONFIG_SYSFS, independently of CONFIG_RPS/XPS. Credits to Stephen Hemminger for a preliminary version of this patch. Tested: without CONFIG_SYSFS (compilation only) with sysfs and without CONFIG_RPS & CONFIG_XPS with sysfs and without CONFIG_RPS with sysfs and without CONFIG_XPS with defaults Signed-off-by: David Decotigny <david.decotigny@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-16 20:15:10 +08:00
txq->trans_timeout++;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
break;
}
}
[PKT_SCHED]: Potential jiffy wrap bug in dev_watchdog(). There is a potential jiffy wraparound bug in the transmit watchdog that is easily avoided by using time_after(). Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-05-17 06:02:12 +08:00
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
if (some_queue_timedout) {
WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
net: Rework netdev_drivername() to avoid warning. This interface uses a temporary buffer, but for no real reason. And now can generate warnings like: net/sched/sch_generic.c: In function dev_watchdog net/sched/sch_generic.c:254:10: warning: unused variable drivername Just return driver->name directly or "". Reported-by: Connor Hansen <cmdkhh@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-06-07 07:41:33 +08:00
dev->name, netdev_drivername(dev), i);
netdev: network device operations infrastructure This patch changes the network device internal API to move adminstrative operations out of the network device structure and into a separate structure. This patch involves some hackery to maintain compatablity between the new and old model, so all 300+ drivers don't have to be changed at once. For drivers that aren't converted yet, the netdevice_ops virt function list still resides in the net_device structure. For old protocols, the new net_device_ops are copied out to the old net_device pointers. After the transistion is completed the nag message can be changed to an WARN_ON, and the compatiablity code can be made configurable. Some function pointers aren't moved: * destructor can't be in net_device_ops because it may need to be referenced after the module is unloaded. * neighbor setup is manipulated in a couple of places that need special consideration * hard_start_xmit is in the fast path for transmit. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-20 13:32:24 +08:00
dev->netdev_ops->ndo_tx_timeout(dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies +
dev->watchdog_timeo)))
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev_hold(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>
2006-06-10 03:20:56 +08:00
netif_tx_unlock(dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev_put(dev);
}
void __netdev_watchdog_up(struct net_device *dev)
{
netdev: network device operations infrastructure This patch changes the network device internal API to move adminstrative operations out of the network device structure and into a separate structure. This patch involves some hackery to maintain compatablity between the new and old model, so all 300+ drivers don't have to be changed at once. For drivers that aren't converted yet, the netdevice_ops virt function list still resides in the net_device structure. For old protocols, the new net_device_ops are copied out to the old net_device pointers. After the transistion is completed the nag message can be changed to an WARN_ON, and the compatiablity code can be made configurable. Some function pointers aren't moved: * destructor can't be in net_device_ops because it may need to be referenced after the module is unloaded. * neighbor setup is manipulated in a couple of places that need special consideration * hard_start_xmit is in the fast path for transmit. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-20 13:32:24 +08:00
if (dev->netdev_ops->ndo_tx_timeout) {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (dev->watchdog_timeo <= 0)
dev->watchdog_timeo = 5*HZ;
[NET]: Make net watchdog timers 1 sec jiffy aligned. round_jiffies for net dev watchdog timer. Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-01 12:28:44 +08:00
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies + dev->watchdog_timeo)))
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev_hold(dev);
}
}
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>
2006-06-10 03:20:56 +08:00
netif_tx_lock_bh(dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (del_timer(&dev->watchdog_timer))
[NET]: dev_put/dev_hold cleanup Get rid of the old __dev_put macro that is just a hold over from pre 2.6 kernel. And turn dev_hold into an inline instead of a macro. Signed-off-by: Stephen Hemminger <shemminger@osdl.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 14:32:28 +08:00
dev_put(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>
2006-06-10 03:20:56 +08:00
netif_tx_unlock_bh(dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
[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>
2007-10-04 07:41:36 +08:00
/**
* netif_carrier_on - set carrier
* @dev: network device
*
Documentation: bring operstate documentation up-to-date Netlink has moved from bitmasks to group numbers long ago. Signed-off-by: Jouke Witteveen <j.witteveen@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-08 00:14:32 +08:00
* 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>
2007-10-04 07:41:36 +08:00
*/
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
void netif_carrier_on(struct net_device *dev)
{
[NET]: fix carrier-on bug? While looking at a net driver with the following construct, if (!netif_carrier_ok(dev)) netif_carrier_on(dev); it stuck me that the netif_carrier_ok() check was redundant, since netif_carrier_on() checks bit __LINK_STATE_NOCARRIER anyway. This is the same reason why netif_queue_stopped() need not be called prior to netif_wake_queue(). This is true, but there is however an unwanted side effect from assuming that netif_carrier_on() can be called multiple times: it touches the watchdog, regardless of pre-existing carrier state. The fix: move watchdog-up inside the bit-cleared code path. Signed-off-by: Jeff Garzik <jgarzik@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-18 14:26:43 +08:00
if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
net: Do not fire linkwatch events until the device is registered. Several device drivers try to do things like netif_carrier_off() before register_netdev() is invoked. This is bogus, but too many drivers do this to fix them all up in one go. Reported-by: Folkert van Heusden <folkert@vanheusden.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-20 07:33:54 +08:00
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
net: core: Expose number of link up/down transitions Expose the number of times the link has been going UP or DOWN, and update the "carrier_changes" counter to be the sum of these two events. While at it, also update the sysfs-class-net documentation to cover: carrier_changes (3.15), carrier_up_count (4.16) and carrier_down_count (4.16) Signed-off-by: David Decotigny <decot@googlers.com> [Florian: * rebase * add documentation * merge carrier_changes with up/down counters] Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-19 01:59:13 +08:00
atomic_inc(&dev->carrier_up_count);
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
linkwatch_fire_event(dev);
[NET]: fix carrier-on bug? While looking at a net driver with the following construct, if (!netif_carrier_ok(dev)) netif_carrier_on(dev); it stuck me that the netif_carrier_ok() check was redundant, since netif_carrier_on() checks bit __LINK_STATE_NOCARRIER anyway. This is the same reason why netif_queue_stopped() need not be called prior to netif_wake_queue(). This is true, but there is however an unwanted side effect from assuming that netif_carrier_on() can be called multiple times: it touches the watchdog, regardless of pre-existing carrier state. The fix: move watchdog-up inside the bit-cleared code path. Signed-off-by: Jeff Garzik <jgarzik@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-18 14:26:43 +08:00
if (netif_running(dev))
__netdev_watchdog_up(dev);
}
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
}
[NET_SCHED]: Move EXPORT_SYMBOL next to exported symbol Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-23 14:10:23 +08:00
EXPORT_SYMBOL(netif_carrier_on);
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
[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>
2007-10-04 07:41:36 +08:00
/**
* netif_carrier_off - clear carrier
* @dev: network device
*
* Device has detected loss of carrier.
*/
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
void netif_carrier_off(struct net_device *dev)
{
net: Do not fire linkwatch events until the device is registered. Several device drivers try to do things like netif_carrier_off() before register_netdev() is invoked. This is bogus, but too many drivers do this to fix them all up in one go. Reported-by: Folkert van Heusden <folkert@vanheusden.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-20 07:33:54 +08:00
if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
net: core: Expose number of link up/down transitions Expose the number of times the link has been going UP or DOWN, and update the "carrier_changes" counter to be the sum of these two events. While at it, also update the sysfs-class-net documentation to cover: carrier_changes (3.15), carrier_up_count (4.16) and carrier_down_count (4.16) Signed-off-by: David Decotigny <decot@googlers.com> [Florian: * rebase * add documentation * merge carrier_changes with up/down counters] Signed-off-by: Florian Fainelli <f.fainelli@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-19 01:59:13 +08:00
atomic_inc(&dev->carrier_down_count);
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
linkwatch_fire_event(dev);
net: Do not fire linkwatch events until the device is registered. Several device drivers try to do things like netif_carrier_off() before register_netdev() is invoked. This is bogus, but too many drivers do this to fix them all up in one go. Reported-by: Folkert van Heusden <folkert@vanheusden.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-20 07:33:54 +08:00
}
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
}
[NET_SCHED]: Move EXPORT_SYMBOL next to exported symbol Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-23 14:10:23 +08:00
EXPORT_SYMBOL(netif_carrier_off);
[NET]: Deinline netif_carrier_{on,off}(). # grep -r 'netif_carrier_o[nf]' linux-2.6.12 | wc -l 246 # size vmlinux.org vmlinux.carrier text data bss dec hex filename 4339634 1054414 259296 5653344 564360 vmlinux.org 4337710 1054414 259296 5651420 563bdc vmlinux.carrier And this ain't an allyesconfig kernel! Signed-off-by: David S. Miller <davem@davemloft.net>
2005-08-12 06:32:53 +08:00
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* "NOOP" scheduler: the best scheduler, recommended for all interfaces
under all circumstances. It is difficult to invent anything faster or
cheaper.
*/
net_sched: drop packets after root qdisc lock is released Qdisc performance suffers when packets are dropped at enqueue() time because drops (kfree_skb()) are done while qdisc lock is held, delaying a dequeue() draining the queue. Nominal throughput can be reduced by 50 % when this happens, at a time we would like the dequeue() to proceed as fast as possible. Even FQ is vulnerable to this problem, while one of FQ goals was to provide some flow isolation. This patch adds a 'struct sk_buff **to_free' parameter to all qdisc->enqueue(), and in qdisc_drop() helper. I measured a performance increase of up to 12 %, but this patch is a prereq so that future batches in enqueue() can fly. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:49 +08:00
static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
struct sk_buff **to_free)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
net_sched: drop packets after root qdisc lock is released Qdisc performance suffers when packets are dropped at enqueue() time because drops (kfree_skb()) are done while qdisc lock is held, delaying a dequeue() draining the queue. Nominal throughput can be reduced by 50 % when this happens, at a time we would like the dequeue() to proceed as fast as possible. Even FQ is vulnerable to this problem, while one of FQ goals was to provide some flow isolation. This patch adds a 'struct sk_buff **to_free' parameter to all qdisc->enqueue(), and in qdisc_drop() helper. I measured a performance increase of up to 12 %, but this patch is a prereq so that future batches in enqueue() can fly. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:49 +08:00
__qdisc_drop(skb, to_free);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return NET_XMIT_CN;
}
net_sched: change "foo* bar" to "foo *bar" "foo* bar" or "foo * bar" should be "foo *bar". Signed-off-by: Yang Yingliang <yangyingliang@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-10 20:55:31 +08:00
static struct sk_buff *noop_dequeue(struct Qdisc *qdisc)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
return NULL;
}
[NET]: Move Qdisc_class_ops and Qdisc_ops in appropriate sections. Qdisc_class_ops are const, and Qdisc_ops are mostly read. Using "const" and "__read_mostly" qualifiers helps to reduce false sharing. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-14 17:44:41 +08:00
struct Qdisc_ops noop_qdisc_ops __read_mostly = {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.id = "noop",
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
pkt_sched: sch_generic: Add generic qdisc->ops->peek() implementation. With feedback from Patrick McHardy. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 15:45:27 +08:00
.peek = noop_dequeue,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.owner = THIS_MODULE,
};
pkt_sched: Add and use qdisc_root() and qdisc_root_lock(). When code wants to lock the qdisc tree state, the logic operation it's doing is locking the top-level qdisc that sits of the root of the netdev_queue. Add qdisc_root_lock() to represent this and convert the easiest cases. In order for this to work out in all cases, we have to hook up the noop_qdisc to a dummy netdev_queue. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 16:42:40 +08:00
static struct netdev_queue noop_netdev_queue = {
net: Use RCU_POINTER_INITIALIZER() to init static variable This pointer is RCU protected, so proper primitives should be used. Signed-off-by: Zhang Yu <zhangyu31@baidu.com> Signed-off-by: Li RongQing <lirongqing@baidu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-25 10:43:06 +08:00
RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc),
pkt_sched: sch_generic: Fix oops in sch_teql After these commands: # modprobe sch_teql # tc qdisc add dev eth0 root teql0 # tc qdisc del dev eth0 root we get an oops in teql_destroy() when spin_lock is taken from a null qdisc_sleeping pointer. It's because at the moment teql0 dev haven't been activated yet, and a qdisc_root_sleeping() is pointing to noop qdisc's netdev_queue with qdisc_sleeping uninitialized. This patch fixes this both for noop and noqueue netdev_queues to avoid similar problems in the future. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-20 14:37:47 +08:00
.qdisc_sleeping = &noop_qdisc,
pkt_sched: Add and use qdisc_root() and qdisc_root_lock(). When code wants to lock the qdisc tree state, the logic operation it's doing is locking the top-level qdisc that sits of the root of the netdev_queue. Add qdisc_root_lock() to represent this and convert the easiest cases. In order for this to work out in all cases, we have to hook up the noop_qdisc to a dummy netdev_queue. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 16:42:40 +08:00
};
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
struct Qdisc noop_qdisc = {
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.flags = TCQ_F_BUILTIN,
[NET] SCHED: Fix whitespace errors. Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-09 22:25:16 +08:00
.ops = &noop_qdisc_ops,
pkt_sched: Kill netdev_queue lock. We can simply use the qdisc->q.lock for all of the qdisc tree synchronization. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:53:03 +08:00
.q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
pkt_sched: Add and use qdisc_root() and qdisc_root_lock(). When code wants to lock the qdisc tree state, the logic operation it's doing is locking the top-level qdisc that sits of the root of the netdev_queue. Add qdisc_root_lock() to represent this and convert the easiest cases. In order for this to work out in all cases, we have to hook up the noop_qdisc to a dummy netdev_queue. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 16:42:40 +08:00
.dev_queue = &noop_netdev_queue,
net_sched: transform qdisc running bit into a seqcount Instead of using a single bit (__QDISC___STATE_RUNNING) in sch->__state, use a seqcount. This adds lockdep support, but more importantly it will allow us to sample qdisc/class statistics without having to grab qdisc root lock. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-07 00:37:15 +08:00
.running = SEQCNT_ZERO(noop_qdisc.running),
net/sched: fix missing spinlock init Under network load, doing : tc qdisc del dev eth0 root triggers : [ 167.193087] BUG: spinlock bad magic on CPU#3, udpflood/4928 [ 167.193139] lock: c15bc324, .magic: 00000000, .owner: <none>/-1, .owner_cpu: -1 [ 167.193193] Pid: 4928, comm: udpflood Not tainted 2.6.36-rc7-11417-g215340c-dirty #323 [ 167.193245] Call Trace: [ 167.193292] [<c13abaa0>] ? printk+0x18/0x20 [ 167.193342] [<c11afb53>] spin_bug+0xa3/0xf0 [ 167.193389] [<c11afcdd>] do_raw_spin_lock+0x7d/0x160 [ 167.193440] [<c1313d4e>] ? __dev_xmit_skb+0x27e/0x2b0 [ 167.193496] [<c107382b>] ? trace_hardirqs_on+0xb/0x10 [ 167.193545] [<c13ae99a>] _raw_spin_lock+0x3a/0x40 [ 167.193593] [<c1313d4e>] ? __dev_xmit_skb+0x27e/0x2b0 [ 167.193641] [<c1313d4e>] __dev_xmit_skb+0x27e/0x2b0 commit 79640a4ca695 (add additional lock to qdisc to increase throughput) forgot to initialize noop_qdisc and noqueue_qdisc busylock Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-16 03:22:34 +08:00
.busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
net: sched: avoid writing on noop_qdisc While noop_qdisc.gso_skb and noop_qdisc.skb_bad_txq are not used in other places, it seems not correct to overwrite their fields in dev_init_scheduler_queue(). noop_qdisc is essentially a shared and read-only object, even if it is not marked as const because of some implementation detail. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-10-10 06:20:50 +08:00
.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),
},
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
};
[NET_SCHED]: Move EXPORT_SYMBOL next to exported symbol Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-23 14:10:23 +08:00
EXPORT_SYMBOL(noop_qdisc);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net: sched: sch: add extack for init callback This patch adds extack support for init callback to prepare per-qdisc specific changes for extack. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:13 +08:00
static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt,
struct netlink_ext_ack *extack)
net: sched: register noqueue qdisc This way users can attach noqueue just like any other qdisc using tc without having to mess with tx_queue_len first. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-28 03:21:38 +08:00
{
/* 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 = {
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.id = "noqueue",
.priv_size = 0,
net: sched: register noqueue qdisc This way users can attach noqueue just like any other qdisc using tc without having to mess with tx_queue_len first. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-28 03:21:38 +08:00
.init = noqueue_init,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
pkt_sched: sch_generic: Add generic qdisc->ops->peek() implementation. With feedback from Patrick McHardy. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 15:45:27 +08:00
.peek = noop_dequeue,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.owner = THIS_MODULE,
};
net_sched: cleanups Cleanup net/sched code to current CodingStyle and practices. Reduce inline abuse Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-20 03:26:56 +08:00
static const u8 prio2band[TC_PRIO_MAX + 1] = {
1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
};
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
/* 3-band FIFO queue: old style, but should be a bit faster than
generic prio+fifo combination.
*/
#define PFIFO_FAST_BANDS 3
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
/*
* Private data for a pfifo_fast scheduler containing:
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
* - rings for priority bands
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
*/
struct pfifo_fast_priv {
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
struct skb_array q[PFIFO_FAST_BANDS];
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
};
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
static inline struct skb_array *band2list(struct pfifo_fast_priv *priv,
int band)
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
{
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
return &priv->q[band];
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
}
net_sched: drop packets after root qdisc lock is released Qdisc performance suffers when packets are dropped at enqueue() time because drops (kfree_skb()) are done while qdisc lock is held, delaying a dequeue() draining the queue. Nominal throughput can be reduced by 50 % when this happens, at a time we would like the dequeue() to proceed as fast as possible. Even FQ is vulnerable to this problem, while one of FQ goals was to provide some flow isolation. This patch adds a 'struct sk_buff **to_free' parameter to all qdisc->enqueue(), and in qdisc_drop() helper. I measured a performance increase of up to 12 %, but this patch is a prereq so that future batches in enqueue() can fly. Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:49 +08:00
static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc,
struct sk_buff **to_free)
[PKT_SCHED]: Add and use prio2list() in the pfifo_fast qdisc prio2list() returns the relevant sk_buff_head for the band specified by the priority for a given skb. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-19 13:58:35 +08:00
{
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
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 09:53:00 +08:00
unsigned int pkt_len = qdisc_pkt_len(skb);
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
int err;
[PKT_SCHED]: Transform pfifo_fast to use generic queue management interface Gives pfifo_fast a byte based backlog. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-19 13:58:15 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
err = skb_array_produce(q, skb);
if (unlikely(err))
return qdisc_drop_cpu(skb, qdisc, to_free);
net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too Since stats updating is always consistent with TCQ_F_CPUSTATS flag, we can disable it at qdisc creation time flipping such bit. In my experiments, if the NOLOCK flag is cleared, per CPU stats accounting does not give any measurable performance gain, but it waste some memory. Let's clear TCQ_F_CPUSTATS together with NOLOCK, when enslaving a NOLOCK qdisc to 'lock' one. Use stats update helper inside pfifo_fast, to cope correctly with TCQ_F_CPUSTATS flag change. As a side effect, q.qlen value for any child qdiscs is always consistent for all lock classfull qdiscs. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-10 20:32:40 +08:00
qdisc_update_stats_at_enqueue(qdisc, pkt_len);
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
return NET_XMIT_SUCCESS;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
net_sched: cleanups Cleanup net/sched code to current CodingStyle and practices. Reduce inline abuse Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-20 03:26:56 +08:00
static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
struct sk_buff *skb = NULL;
int band;
sched: remove qdisc arg from __qdisc_dequeue_head Moves qdisc stat accouting to qdisc_dequeue_head. The only direct caller of the __qdisc_dequeue_head version open-codes this now. This allows us to later use __qdisc_dequeue_head as a replacement of __skb_dequeue() (which operates on sk_buff_head list). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-18 06:57:32 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
struct skb_array *q = band2list(priv, band);
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
if (__skb_array_empty(q))
continue;
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
pfifo_fast: drop unneeded additional lock on dequeue After the previous patch, for NOLOCK qdiscs, q->seqlock is always held when the dequeue() is invoked, we can drop any additional locking to protect such operation. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 22:24:37 +08:00
skb = __skb_array_consume(q);
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
}
if (likely(skb)) {
net: sched: when clearing NOLOCK, clear TCQ_F_CPUSTATS, too Since stats updating is always consistent with TCQ_F_CPUSTATS flag, we can disable it at qdisc creation time flipping such bit. In my experiments, if the NOLOCK flag is cleared, per CPU stats accounting does not give any measurable performance gain, but it waste some memory. Let's clear TCQ_F_CPUSTATS together with NOLOCK, when enslaving a NOLOCK qdisc to 'lock' one. Use stats update helper inside pfifo_fast, to cope correctly with TCQ_F_CPUSTATS flag change. As a side effect, q.qlen value for any child qdiscs is always consistent for all lock classfull qdiscs. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-10 20:32:40 +08:00
qdisc_update_stats_at_dequeue(qdisc, skb);
net: sched: add empty status flag for NOLOCK qdisc The queue is marked not empty after acquiring the seqlock, and it's up to the NOLOCK qdisc clearing such flag on dequeue. Since the empty status lays on the same cache-line of the seqlock, it's always hot on cache during the updates. This makes the empty flag update a little bit loosy. Given the lack of synchronization between enqueue and dequeue, this is unavoidable. v2 -> v3: - qdisc_is_empty() has a const argument (Eric) v1 -> v2: - use really an 'empty' flag instead of 'not_empty', as suggested by Eric Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Ivan Vecera <ivecera@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-22 23:01:55 +08:00
} else {
qdisc->empty = true;
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
}
[PKT_SCHED]: Cleanup pfifo_fast qdisc and remove unnecessary code Removes the skb trimming code which is not needed since we never touch the skb upon failure. Removes unnecessary initializers, and simplifies the code a bit. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-06-19 13:58:53 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
return skb;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
net_sched: cleanups Cleanup net/sched code to current CodingStyle and practices. Reduce inline abuse Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-20 03:26:56 +08:00
static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc)
pkt_sched: sch_generic: Add generic qdisc->ops->peek() implementation. With feedback from Patrick McHardy. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 15:45:27 +08:00
{
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
struct sk_buff *skb = NULL;
int band;
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) {
struct skb_array *q = band2list(priv, band);
pkt_sched: sch_generic: Add generic qdisc->ops->peek() implementation. With feedback from Patrick McHardy. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 15:45:27 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
skb = __skb_array_peek(q);
pkt_sched: sch_generic: Add generic qdisc->ops->peek() implementation. With feedback from Patrick McHardy. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 15:45:27 +08:00
}
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
return skb;
pkt_sched: sch_generic: Add generic qdisc->ops->peek() implementation. With feedback from Patrick McHardy. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 15:45:27 +08:00
}
net_sched: cleanups Cleanup net/sched code to current CodingStyle and practices. Reduce inline abuse Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-20 03:26:56 +08:00
static void pfifo_fast_reset(struct Qdisc *qdisc)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
int i, band;
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
for (band = 0; band < PFIFO_FAST_BANDS; band++) {
struct skb_array *q = band2list(priv, band);
struct sk_buff *skb;
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
net_sched: properly check for empty skb array on error path First, the check of &q->ring.queue against NULL is wrong, it is always false. We should check the value rather than the address. Secondly, we need the same check in pfifo_fast_reset() too, as both ->reset() and ->destroy() are called in qdisc_destroy(). Fixes: c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array") Reported-by: syzbot <syzkaller@googlegroups.com> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-19 06:34:26 +08:00
/* 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;
pfifo_fast: drop unneeded additional lock on dequeue After the previous patch, for NOLOCK qdiscs, q->seqlock is always held when the dequeue() is invoked, we can drop any additional locking to protect such operation. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 22:24:37 +08:00
while ((skb = __skb_array_consume(q)) != NULL)
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
kfree_skb(skb);
}
for_each_possible_cpu(i) {
struct gnet_stats_queue *q = per_cpu_ptr(qdisc->cpu_qstats, i);
q->backlog = 0;
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb)
{
struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
net_sched: cleanups Cleanup net/sched code to current CodingStyle and practices. Reduce inline abuse Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-20 03:26:56 +08:00
memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
pkt_sched: Stop using NLA_PUT*(). These macros contain a hidden goto, and are thus extremely error prone and make code hard to audit. Signed-off-by: David S. Miller <davem@davemloft.net>
2012-03-29 17:11:39 +08:00
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
return skb->len;
nla_put_failure:
return -1;
}
net: sched: sch: add extack for init callback This patch adds extack support for init callback to prepare per-qdisc specific changes for extack. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:13 +08:00
static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt,
struct netlink_ext_ack *extack)
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
{
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len;
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
int prio;
/* guard against zero length rings */
if (!qlen)
return -EINVAL;
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
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;
}
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
net_sched: TCQ_F_CAN_BYPASS generalization Now qdisc stab is handled before TCQ_F_CAN_BYPASS test in __dev_xmit_skb(), we can generalize TCQ_F_CAN_BYPASS to other qdiscs than pfifo_fast : pfifo, bfifo, pfifo_head_drop and sfq SFQ is special because it can have external classifiers, and in these cases, we cannot bypass queue discipline (packet could be dropped by classifier) without admin asking it, or further changes. Its worth doing this, especially for SFQ, avoiding dirtying memory in case no packets are already waiting in queue. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-22 08:26:09 +08:00
/* Can by-pass the queue discipline */
qdisc->flags |= TCQ_F_CAN_BYPASS;
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
return 0;
}
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
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.
*/
net_sched: properly check for empty skb array on error path First, the check of &q->ring.queue against NULL is wrong, it is always false. We should check the value rather than the address. Secondly, we need the same check in pfifo_fast_reset() too, as both ->reset() and ->destroy() are called in qdisc_destroy(). Fixes: c5ad119fb6c0 ("net: sched: pfifo_fast use skb_array") Reported-by: syzbot <syzkaller@googlegroups.com> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-19 06:34:26 +08:00
if (!q->ring.queue)
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
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);
}
}
net_sched: implement ->change_tx_queue_len() for pfifo_fast pfifo_fast used to drop based on qdisc_dev(qdisc)->tx_queue_len, so we have to resize skb array when we change tx_queue_len. Other qdiscs which read tx_queue_len are fine because they all save it to sch->limit or somewhere else in qdisc during init. They don't have to implement this, it is nicer if they do so that users don't have to re-configure qdisc after changing tx_queue_len. Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-26 10:26:24 +08:00
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);
}
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
struct Qdisc_ops pfifo_fast_ops __read_mostly = {
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
.id = "pfifo_fast",
Speed-up pfifo_fast lookup using a private bitmap Maintain a per-qdisc bitmap for pfifo_fast giving availability of skbs for each band. This allows faster lookup for a skb when there are no high priority skbs. Also, it helps in (rare) cases when there are no skbs on the list, where an immediate lookup is faster than iterating through the three bands. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-08-19 05:55:59 +08:00
.priv_size = sizeof(struct pfifo_fast_priv),
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
.enqueue = pfifo_fast_enqueue,
.dequeue = pfifo_fast_dequeue,
pkt_sched: sch_generic: Add generic qdisc->ops->peek() implementation. With feedback from Patrick McHardy. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-10-31 15:45:27 +08:00
.peek = pfifo_fast_peek,
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
.init = pfifo_fast_init,
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
.destroy = pfifo_fast_destroy,
Revert "pkt_sched: Make default qdisc nonshared-multiqueue safe." This reverts commit a0c80b80e0fb48129e4e9d6a9ede914f9ff1850d. After discussions with Jamal and Herbert on netdev, we should provide at least minimal prioritization at the qdisc level even in multiqueue situations. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-22 00:56:13 +08:00
.reset = pfifo_fast_reset,
.dump = pfifo_fast_dump,
net_sched: implement ->change_tx_queue_len() for pfifo_fast pfifo_fast used to drop based on qdisc_dev(qdisc)->tx_queue_len, so we have to resize skb array when we change tx_queue_len. Other qdiscs which read tx_queue_len are fine because they all save it to sch->limit or somewhere else in qdisc during init. They don't have to implement this, it is nicer if they do so that users don't have to re-configure qdisc after changing tx_queue_len. Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-26 10:26:24 +08:00
.change_tx_queue_len = pfifo_fast_change_tx_queue_len,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
.owner = THIS_MODULE,
net: sched: pfifo_fast use skb_array This converts the pfifo_fast qdisc to use the skb_array data structure and set the lockless qdisc bit. pfifo_fast is the first qdisc to support the lockless bit that can be a child of a qdisc requiring locking. So we add logic to clear the lock bit on initialization in these cases when the qdisc graft operation occurs. This also removes the logic used to pick the next band to dequeue from and instead just checks a per priority array for packets from top priority to lowest. This might need to be a bit more clever but seems to work for now. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:58:19 +08:00
.static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
};
net: sched: use pfifo_fast for non real queues Some devices declare a high number of TX queues, then set a much lower real_num_tx_queues This cause setups using fq_codel, sfq or fq as the default qdisc to consume more memory than really needed. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-03 00:21:43 +08:00
EXPORT_SYMBOL(pfifo_fast_ops);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
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 09:02:56 +08:00
static struct lock_class_key qdisc_tx_busylock;
net_sched: transform qdisc running bit into a seqcount Instead of using a single bit (__QDISC___STATE_RUNNING) in sch->__state, use a seqcount. This adds lockdep support, but more importantly it will allow us to sample qdisc/class statistics without having to grab qdisc root lock. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-07 00:37:15 +08:00
static struct lock_class_key qdisc_running_key;
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 09:02:56 +08:00
pkt_sched: Remove 'dev' member of struct Qdisc. It can be obtained via the netdev_queue. So create a helper routine, qdisc_dev(), to make the transformations nicer looking. Now, qdisc_alloc() now no longer needs a net_device pointer argument. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:06:30 +08:00
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
net: sch: api: add extack support in qdisc_alloc This patch adds extack support for the function qdisc_alloc which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_alloc failed. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:20 +08:00
const struct Qdisc_ops *ops,
struct netlink_ext_ack *extack)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
void *p;
struct Qdisc *sch;
net_sched: reduce fifo qdisc size Because of various alignements [SLUB / qdisc], we use 512 bytes of memory for one {p|b}fifo qdisc, instead of 256 bytes on 64bit arches and 192 bytes on 32bit ones. Move the "u32 limit" inside "struct Qdisc" (no impact on other qdiscs) Change qdisc_alloc(), first trying a regular allocation before an oversized one. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-04 03:10:02 +08:00
unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
[PKT_SCHED]: Cleanup qdisc creation and alignment macros Adds qdisc_alloc() to share code between qdisc_create() and qdisc_create_dflt(). Hides the qdisc alignment behind macros and makes use of them. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-06 05:15:09 +08:00
int err = -ENOBUFS;
net/sched: Check for null dev_queue on create flow In qdisc_alloc() the dev_queue pointer was used without any checks being performed. If qdisc_create() gets a null dev_queue pointer, it just passes it along to qdisc_alloc(), leading to a crash. That happens if a root qdisc implements select_queue() and returns a null dev_queue pointer for an "invalid handle", for example, or if the dev_queue associated with the parent qdisc is null. This patch is in preparation for the next in this series, where select_queue() is being added to mqprio and as it may return a null dev_queue. Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com> Tested-by: Henrik Austad <henrik@austad.us> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-10-17 09:01:23 +08:00
struct net_device *dev;
if (!dev_queue) {
net: sch: api: add extack support in qdisc_alloc This patch adds extack support for the function qdisc_alloc which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_alloc failed. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:20 +08:00
NL_SET_ERR_MSG(extack, "No device queue given");
net/sched: Check for null dev_queue on create flow In qdisc_alloc() the dev_queue pointer was used without any checks being performed. If qdisc_create() gets a null dev_queue pointer, it just passes it along to qdisc_alloc(), leading to a crash. That happens if a root qdisc implements select_queue() and returns a null dev_queue pointer for an "invalid handle", for example, or if the dev_queue associated with the parent qdisc is null. This patch is in preparation for the next in this series, where select_queue() is being added to mqprio and as it may return a null dev_queue. Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com> Tested-by: Henrik Austad <henrik@austad.us> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-10-17 09:01:23 +08:00
err = -EINVAL;
goto errout;
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net/sched: Check for null dev_queue on create flow In qdisc_alloc() the dev_queue pointer was used without any checks being performed. If qdisc_create() gets a null dev_queue pointer, it just passes it along to qdisc_alloc(), leading to a crash. That happens if a root qdisc implements select_queue() and returns a null dev_queue pointer for an "invalid handle", for example, or if the dev_queue associated with the parent qdisc is null. This patch is in preparation for the next in this series, where select_queue() is being added to mqprio and as it may return a null dev_queue. Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com> Tested-by: Henrik Austad <henrik@austad.us> Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2017-10-17 09:01:23 +08:00
dev = dev_queue->dev;
net sched: use xps information for qdisc NUMA affinity Allocate qdisc memory according to NUMA properties of cpus included in xps map. To be effective, qdisc should be (re)setup after changes of /sys/class/net/eth<n>/queues/tx-<n>/xps_cpus I added a numa_node field in struct netdev_queue, containing NUMA node if all cpus included in xps_cpus share same node, else -1. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-11-29 16:14:37 +08:00
p = kzalloc_node(size, GFP_KERNEL,
netdev_queue_numa_node_read(dev_queue));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (!p)
[PKT_SCHED]: Cleanup qdisc creation and alignment macros Adds qdisc_alloc() to share code between qdisc_create() and qdisc_create_dflt(). Hides the qdisc alignment behind macros and makes use of them. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-06 05:15:09 +08:00
goto errout;
sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
net_sched: reduce fifo qdisc size Because of various alignements [SLUB / qdisc], we use 512 bytes of memory for one {p|b}fifo qdisc, instead of 256 bytes on 64bit arches and 192 bytes on 32bit ones. Move the "u32 limit" inside "struct Qdisc" (no impact on other qdiscs) Change qdisc_alloc(), first trying a regular allocation before an oversized one. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-04 03:10:02 +08:00
/* if we got non aligned memory, ask more and do alignment ourself */
if (sch != p) {
kfree(p);
p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL,
netdev_queue_numa_node_read(dev_queue));
if (!p)
goto errout;
sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
sch->padded = (char *) sch - (char *) p;
}
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
__skb_queue_head_init(&sch->gso_skb);
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
__skb_queue_head_init(&sch->skb_bad_txq);
sched: add and use qdisc_skb_head helpers This change replaces sk_buff_head struct in Qdiscs with new qdisc_skb_head. Its similar to the skb_buff_head api, but does not use skb->prev pointers. Qdiscs will commonly enqueue at the tail of a list and dequeue at head. While skb_buff_head works fine for this, enqueue/dequeue needs to also adjust the prev pointer of next element. The ->prev pointer is not required for qdiscs so we can just leave it undefined and avoid one cacheline write access for en/dequeue. Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-09-18 06:57:34 +08:00
qdisc_skb_head_init(&sch->q);
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 09:02:56 +08:00
net: sched: a dflt qdisc may be used with per cpu stats Enable dflt qdisc support for per cpu stats before this patch a dflt qdisc was required to use the global statistics qstats and bstats. This adds a static flags field to qdisc_ops that is propagated into qdisc->flags in qdisc allocate call. This allows the allocation block to completely allocate the qdisc object so we don't have dangling allocations after qdisc init. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:26 +08:00
if (ops->static_flags & TCQ_F_CPUSTATS) {
sch->cpu_bstats =
netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
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;
}
}
net: add additional lock to qdisc to increase throughput When many cpus compete for sending frames on a given qdisc, the qdisc spinlock suffers from very high contention. The cpu owning __QDISC_STATE_RUNNING bit has same priority to acquire the lock, and cannot dequeue packets fast enough, since it must wait for this lock for each dequeued packet. One solution to this problem is to force all cpus spinning on a second lock before trying to get the main lock, when/if they see __QDISC_STATE_RUNNING already set. The owning cpu then compete with at most one other cpu for the main lock, allowing for higher dequeueing rate. Based on a previous patch from Alexander Duyck. I added the heuristic to avoid the atomic in fast path, and put the new lock far away from the cache line used by the dequeue worker. Also try to release the busylock lock as late as possible. Tests with following script gave a boost from ~50.000 pps to ~600.000 pps on a dual quad core machine (E5450 @3.00GHz), tg3 driver. (A single netperf flow can reach ~800.000 pps on this platform) for j in `seq 0 3`; do for i in `seq 0 7`; do netperf -H 192.168.0.1 -t UDP_STREAM -l 60 -N -T $i -- -m 6 & done done Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Acked-by: Alexander Duyck <alexander.h.duyck@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-02 20:09:29 +08:00
spin_lock_init(&sch->busylock);
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 09:02:56 +08:00
lockdep_set_class(&sch->busylock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
sched: replace __QDISC_STATE_RUNNING bit with a spin lock So that we can use lockdep on it. The newly introduced sequence lock has the same scope of busylock, so it shares the same lockdep annotation, but it's only used for NOLOCK qdiscs. With this changeset we acquire such lock in the control path around flushing operation (qdisc reset), to allow more NOLOCK qdisc perf improvement in the next patch. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 22:24:36 +08:00
/* seqlock has the same scope of busylock, for NOLOCK qdisc */
spin_lock_init(&sch->seqlock);
lockdep_set_class(&sch->busylock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
net_sched: transform qdisc running bit into a seqcount Instead of using a single bit (__QDISC___STATE_RUNNING) in sch->__state, use a seqcount. This adds lockdep support, but more importantly it will allow us to sample qdisc/class statistics without having to grab qdisc root lock. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-07 00:37:15 +08:00
seqcount_init(&sch->running);
lockdep_set_class(&sch->running,
dev->qdisc_running_key ?: &qdisc_running_key);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sch->ops = ops;
net: sched: a dflt qdisc may be used with per cpu stats Enable dflt qdisc support for per cpu stats before this patch a dflt qdisc was required to use the global statistics qstats and bstats. This adds a static flags field to qdisc_ops that is propagated into qdisc->flags in qdisc allocate call. This allows the allocation block to completely allocate the qdisc object so we don't have dangling allocations after qdisc init. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:26 +08:00
sch->flags = ops->static_flags;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sch->enqueue = ops->enqueue;
sch->dequeue = ops->dequeue;
netdev: Create netdev_queue abstraction. A netdev_queue is an entity managed by a qdisc. Currently there is one RX and one TX queue, and a netdev_queue merely contains a backpointer to the net_device. The Qdisc struct is augmented with a netdev_queue pointer as well. Eventually the 'dev' Qdisc member will go away and we will have the resulting hierarchy: net_device --> netdev_queue --> Qdisc Also, qdisc_alloc() and qdisc_create_dflt() now take a netdev_queue pointer argument. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 07:55:56 +08:00
sch->dev_queue = dev_queue;
net: sched: add empty status flag for NOLOCK qdisc The queue is marked not empty after acquiring the seqlock, and it's up to the NOLOCK qdisc clearing such flag on dequeue. Since the empty status lays on the same cache-line of the seqlock, it's always hot on cache during the updates. This makes the empty flag update a little bit loosy. Given the lack of synchronization between enqueue and dequeue, this is unavoidable. v2 -> v3: - qdisc_is_empty() has a const argument (Eric) v1 -> v2: - use really an 'empty' flag instead of 'not_empty', as suggested by Eric Signed-off-by: Paolo Abeni <pabeni@redhat.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Reviewed-by: Ivan Vecera <ivecera@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-22 23:01:55 +08:00
sch->empty = true;
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 09:02:56 +08:00
dev_hold(dev);
net, sched: convert Qdisc.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Elena Reshetova <elena.reshetova@intel.com> Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com> Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: David Windsor <dwindsor@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-07-04 20:53:07 +08:00
refcount_set(&sch->refcnt, 1);
[PKT_SCHED]: Cleanup qdisc creation and alignment macros Adds qdisc_alloc() to share code between qdisc_create() and qdisc_create_dflt(). Hides the qdisc alignment behind macros and makes use of them. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-06 05:15:09 +08:00
return sch;
net: sched: a dflt qdisc may be used with per cpu stats Enable dflt qdisc support for per cpu stats before this patch a dflt qdisc was required to use the global statistics qstats and bstats. This adds a static flags field to qdisc_ops that is propagated into qdisc->flags in qdisc allocate call. This allows the allocation block to completely allocate the qdisc object so we don't have dangling allocations after qdisc init. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:26 +08:00
errout1:
kfree(p);
[PKT_SCHED]: Cleanup qdisc creation and alignment macros Adds qdisc_alloc() to share code between qdisc_create() and qdisc_create_dflt(). Hides the qdisc alignment behind macros and makes use of them. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-06 05:15:09 +08:00
errout:
pkt_sched: ERR_PTR() ususally encodes an negative errno, not positive. Note, in the following patch, 'err' is initialized as: int err = -ENOBUFS; Signed-off-by: WANG Cong <wcong@critical-links.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-06-28 10:51:35 +08:00
return ERR_PTR(err);
[PKT_SCHED]: Cleanup qdisc creation and alignment macros Adds qdisc_alloc() to share code between qdisc_create() and qdisc_create_dflt(). Hides the qdisc alignment behind macros and makes use of them. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-06 05:15:09 +08:00
}
net_sched: remove the unused parameter of qdisc_create_dflt() The first parameter dev isn't in use in qdisc_create_dflt(). Signed-off-by: Changli Gao <xiaosuo@gmail.com> Acked-by: Jamal Hadi Salim <hadi@cyberus.ca> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-16 21:04:08 +08:00
struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
qdisc: make args to qdisc_create_default const Fixes warnings introduced by the qdisc default patch. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-01 01:15:50 +08:00
const struct Qdisc_ops *ops,
net: sch: api: add extack support in qdisc_create_dflt This patch adds extack support for the function qdisc_create_dflt which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_create_dflt failed. The function qdisc_create_dflt will also call an init callback which can fail by any per-qdisc specific handling. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:21 +08:00
unsigned int parentid,
struct netlink_ext_ack *extack)
[PKT_SCHED]: Cleanup qdisc creation and alignment macros Adds qdisc_alloc() to share code between qdisc_create() and qdisc_create_dflt(). Hides the qdisc alignment behind macros and makes use of them. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-06 05:15:09 +08:00
{
struct Qdisc *sch;
[NET] SCHED: Fix whitespace errors. Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-09 22:25:16 +08:00
net: sch: api: add extack support in qdisc_create_dflt This patch adds extack support for the function qdisc_create_dflt which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_create_dflt failed. The function qdisc_create_dflt will also call an init callback which can fail by any per-qdisc specific handling. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:21 +08:00
if (!try_module_get(ops->owner)) {
NL_SET_ERR_MSG(extack, "Failed to increase module reference counter");
qdisc: fix a module refcount leak in qdisc_create_dflt() Should qdisc_alloc() fail, we must release the module refcount we got right before. Fixes: 6da7c8fcbcbd ("qdisc: allow setting default queuing discipline") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-25 00:39:02 +08:00
return NULL;
net: sch: api: add extack support in qdisc_create_dflt This patch adds extack support for the function qdisc_create_dflt which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_create_dflt failed. The function qdisc_create_dflt will also call an init callback which can fail by any per-qdisc specific handling. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:21 +08:00
}
qdisc: allow setting default queuing discipline By default, the pfifo_fast queue discipline has been used by default for all devices. But we have better choices now. This patch allow setting the default queueing discipline with sysctl. This allows easy use of better queueing disciplines on all devices without having to use tc qdisc scripts. It is intended to allow an easy path for distributions to make fq_codel or sfq the default qdisc. This patch also makes pfifo_fast more of a first class qdisc, since it is now possible to manually override the default and explicitly use pfifo_fast. The behavior for systems who do not use the sysctl is unchanged, they still get pfifo_fast Also removes leftover random # in sysctl net core. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-28 07:19:08 +08:00
net: sch: api: add extack support in qdisc_create_dflt This patch adds extack support for the function qdisc_create_dflt which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_create_dflt failed. The function qdisc_create_dflt will also call an init callback which can fail by any per-qdisc specific handling. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:21 +08:00
sch = qdisc_alloc(dev_queue, ops, extack);
qdisc: fix a module refcount leak in qdisc_create_dflt() Should qdisc_alloc() fail, we must release the module refcount we got right before. Fixes: 6da7c8fcbcbd ("qdisc: allow setting default queuing discipline") Signed-off-by: Eric Dumazet <edumazet@google.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-25 00:39:02 +08:00
if (IS_ERR(sch)) {
module_put(ops->owner);
return NULL;
}
[NET_SCHED]: Set parent classid in default qdiscs Set parent classids in default qdiscs to allow walking up the tree from outside the qdiscs. This is needed by the next patch. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-30 09:35:18 +08:00
sch->parent = parentid;
[PKT_SCHED]: Cleanup qdisc creation and alignment macros Adds qdisc_alloc() to share code between qdisc_create() and qdisc_create_dflt(). Hides the qdisc alignment behind macros and makes use of them. Signed-off-by: Thomas Graf <tgraf@suug.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-06 05:15:09 +08:00
net: sch: api: add extack support in qdisc_create_dflt This patch adds extack support for the function qdisc_create_dflt which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_create_dflt failed. The function qdisc_create_dflt will also call an init callback which can fail by any per-qdisc specific handling. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:21 +08:00
if (!ops->init || ops->init(sch, NULL, extack) == 0)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return sch;
net: sched: rename qdisc_destroy() to qdisc_put() Current implementation of qdisc_destroy() decrements Qdisc reference counter and only actually destroy Qdisc if reference counter value reached zero. Rename qdisc_destroy() to qdisc_put() in order for it to better describe the way in which this function currently implemented and used. Extract code that deallocates Qdisc into new private qdisc_destroy() function. It is intended to be shared between regular qdisc_put() and its unlocked version that is introduced in next patch in this series. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:50 +08:00
qdisc_put(sch);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return NULL;
}
[NET_SCHED]: Move EXPORT_SYMBOL next to exported symbol Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-23 14:10:23 +08:00
EXPORT_SYMBOL(qdisc_create_dflt);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pkt_sched: Use qdisc_lock() on already sampled root qdisc. Based upon a bug report by Jeff Kirsher. Don't use qdisc_root_lock() in these cases as the root qdisc could have been changed, and we'd thus lock the wrong object. Tested by Emil S Tantilov who confirms that this seems to fix the problem. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-03 11:02:43 +08:00
/* Under qdisc_lock(qdisc) and BH! */
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
void qdisc_reset(struct Qdisc *qdisc)
{
[NET]: Move Qdisc_class_ops and Qdisc_ops in appropriate sections. Qdisc_class_ops are const, and Qdisc_ops are mostly read. Using "const" and "__read_mostly" qualifiers helps to reduce false sharing. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-11-14 17:44:41 +08:00
const struct Qdisc_ops *ops = qdisc->ops;
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
struct sk_buff *skb, *tmp;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (ops->reset)
ops->reset(qdisc);
pkt_sched: sch_generic: Kfree gso_skb in qdisc_reset() Since gso_skb is re-used for qdisc_peek_dequeued(), and this skb is counted in the qdisc->q.qlen, it has to be kfreed during qdisc_reset() when qlen is zeroed. With help from David S. Miller <davem@davemloft.net> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-03 18:52:50 +08:00
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
skb_queue_walk_safe(&qdisc->gso_skb, skb, tmp) {
__skb_unlink(skb, &qdisc->gso_skb);
kfree_skb_list(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 09:44:21 +08:00
}
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
skb_queue_walk_safe(&qdisc->skb_bad_txq, skb, tmp) {
__skb_unlink(skb, &qdisc->skb_bad_txq);
kfree_skb_list(skb);
}
net_sched: generalize bulk dequeue When qdisc bulk dequeue was added in linux-3.18 (commit 5772e9a3463b "qdisc: bulk dequeue support for qdiscs with TCQ_F_ONETXQUEUE"), it was constrained to some specific qdiscs. With some extra care, we can extend this to all qdiscs, so that typical traffic shaping solutions can benefit from small batches (8 packets in this patch). For example, HTB is often used on some multi queue device. And bonding/team are multi queue devices... Idea is to bulk-dequeue packets mapping to the same transmit queue. This brings between 35 and 80 % performance increase in HTB setup under pressure on a bonding setup : 1) NUMA node contention : 610,000 pps -> 1,110,000 pps 2) No node contention : 1,380,000 pps -> 1,930,000 pps Now we should work to add batches on the enqueue() side ;) Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Jesper Dangaard Brouer <brouer@redhat.com> Cc: Hannes Frederic Sowa <hannes@stressinduktion.org> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-22 14:16:52 +08:00
qdisc->q.qlen = 0;
net_sched: always reset qdisc backlog in qdisc_reset() SKB stored in qdisc->gso_skb also counted into backlog. Some qdiscs don't reset backlog to zero in ->reset(), for example sfq just dequeue and free all queued skb. Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Fixes: 2ccccf5fb43f ("net_sched: update hierarchical backlog too") Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-20 20:45:36 +08:00
qdisc->qstats.backlog = 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
[NET_SCHED]: Move EXPORT_SYMBOL next to exported symbol Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-01-23 14:10:23 +08:00
EXPORT_SYMBOL(qdisc_reset);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
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>
2018-01-16 06:12:09 +08:00
void qdisc_free(struct Qdisc *qdisc)
gen_estimator: deadlock fix One of my test machine got a deadlock during "tc" sessions, adding/deleting classes & filters, using traffic estimators. After some analysis, I believe we have a potential use after free case in est_timer() : spin_lock(e->stats_lock); << HERE >> read_lock(&est_lock); if (e->bstats == NULL) << TEST >> goto skip; Test is done a bit late, because after estimator is killed, and before rcu grace period elapsed, we might already have freed/reuse memory where e->stats_locks points to (some qdisc->q.lock) A possible fix is to respect a rcu grace period at Qdisc dismantle time. On 64bit, sizeof(struct Qdisc) is exactly 192 bytes. Adding 16 bytes to it (for struct rcu_head) is a problem because it might change performance, given QDISC_ALIGNTO is 32 bytes. This is why I also change QDISC_ALIGNTO to 64 bytes, to satisfy most current alignment requirements. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-31 15:06:04 +08:00
{
net: sched: fix missing free per cpu on qstats When a qdisc is using per cpu stats (currently just the ingress qdisc) only the bstats are being freed. This also free's the qstats. Fixes: b0ab6f92752b9f9d8 ("net: sched: enable per cpu qstats") Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-06 01:11:36 +08:00
if (qdisc_is_percpu_stats(qdisc)) {
net: sched: make bstats per cpu and estimator RCU safe In order to run qdisc's without locking statistics and estimators need to be handled correctly. To resolve bstats make the statistics per cpu. And because this is only needed for qdiscs that are running without locks which is not the case for most qdiscs in the near future only create percpu stats when qdiscs set the TCQ_F_CPUSTATS flag. Next because estimators use the bstats to calculate packets per second and bytes per second the estimator code paths are updated to use the per cpu statistics. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-29 02:52:56 +08:00
free_percpu(qdisc->cpu_bstats);
net: sched: fix missing free per cpu on qstats When a qdisc is using per cpu stats (currently just the ingress qdisc) only the bstats are being freed. This also free's the qstats. Fixes: b0ab6f92752b9f9d8 ("net: sched: enable per cpu qstats") Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Eric Dumazet <edumazet@google.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-01-06 01:11:36 +08:00
free_percpu(qdisc->cpu_qstats);
}
net: sched: make bstats per cpu and estimator RCU safe In order to run qdisc's without locking statistics and estimators need to be handled correctly. To resolve bstats make the statistics per cpu. And because this is only needed for qdiscs that are running without locks which is not the case for most qdiscs in the near future only create percpu stats when qdiscs set the TCQ_F_CPUSTATS flag. Next because estimators use the bstats to calculate packets per second and bytes per second the estimator code paths are updated to use the per cpu statistics. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-29 02:52:56 +08:00
gen_estimator: deadlock fix One of my test machine got a deadlock during "tc" sessions, adding/deleting classes & filters, using traffic estimators. After some analysis, I believe we have a potential use after free case in est_timer() : spin_lock(e->stats_lock); << HERE >> read_lock(&est_lock); if (e->bstats == NULL) << TEST >> goto skip; Test is done a bit late, because after estimator is killed, and before rcu grace period elapsed, we might already have freed/reuse memory where e->stats_locks points to (some qdisc->q.lock) A possible fix is to respect a rcu grace period at Qdisc dismantle time. On 64bit, sizeof(struct Qdisc) is exactly 192 bytes. Adding 16 bytes to it (for struct rcu_head) is a problem because it might change performance, given QDISC_ALIGNTO is 32 bytes. This is why I also change QDISC_ALIGNTO to 64 bytes, to satisfy most current alignment requirements. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-03-31 15:06:04 +08:00
kfree((char *) qdisc - qdisc->padded);
}
net: sched: make function qdisc_free_cb() static Fixes the following sparse warning: net/sched/sch_generic.c:944:6: warning: symbol 'qdisc_free_cb' was not declared. Should it be static? Fixes: 3a7d0d07a386 ("net: sched: extend Qdisc with rcu") Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-27 22:47:56 +08:00
static void qdisc_free_cb(struct rcu_head *head)
net: sched: extend Qdisc with rcu Currently, Qdisc API functions assume that users have rtnl lock taken. To implement rtnl unlocked classifiers update interface, Qdisc API must be extended with functions that do not require rtnl lock. Extend Qdisc structure with rcu. Implement special version of put function qdisc_put_unlocked() that is called without rtnl lock taken. This function only takes rtnl lock if Qdisc reference counter reached zero and is intended to be used as optimization. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:51 +08:00
{
struct Qdisc *q = container_of(head, struct Qdisc, rcu);
qdisc_free(q);
}
net: sched: rename qdisc_destroy() to qdisc_put() Current implementation of qdisc_destroy() decrements Qdisc reference counter and only actually destroy Qdisc if reference counter value reached zero. Rename qdisc_destroy() to qdisc_put() in order for it to better describe the way in which this function currently implemented and used. Extract code that deallocates Qdisc into new private qdisc_destroy() function. It is intended to be shared between regular qdisc_put() and its unlocked version that is introduced in next patch in this series. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:50 +08:00
static void qdisc_destroy(struct Qdisc *qdisc)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
pkt_sched: Perform bulk of qdisc destruction in RCU. This allows less strict control of access to the qdisc attached to a netdev_queue. It is even allowed to enqueue into a qdisc which is in the process of being destroyed. The RCU handler will toss out those packets. We will need this to handle sharing of a qdisc amongst multiple TX queues. In such a setup the lock has to be shared, so will be inside of the qdisc itself. At which point the netdev_queue lock cannot be used to hard synchronize access to the ->qdisc pointer. One operation we have to keep inside of qdisc_destroy() is the list deletion. It is the only piece of state visible after the RCU quiesce period, so we have to undo it early and under the appropriate locking. The operations in the RCU handler do not need any looking because the qdisc tree is no longer visible to anything at that point. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:47:45 +08:00
const struct Qdisc_ops *ops = qdisc->ops;
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
struct sk_buff *skb, *tmp;
pkt_sched: Perform bulk of qdisc destruction in RCU. This allows less strict control of access to the qdisc attached to a netdev_queue. It is even allowed to enqueue into a qdisc which is in the process of being destroyed. The RCU handler will toss out those packets. We will need this to handle sharing of a qdisc amongst multiple TX queues. In such a setup the lock has to be shared, so will be inside of the qdisc itself. At which point the netdev_queue lock cannot be used to hard synchronize access to the ->qdisc pointer. One operation we have to keep inside of qdisc_destroy() is the list deletion. It is the only piece of state visible after the RCU quiesce period, so we have to undo it early and under the appropriate locking. The operations in the RCU handler do not need any looking because the qdisc tree is no longer visible to anything at that point. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:47:45 +08:00
pkt_sched: Fix build with NET_SCHED disabled. The stab bits can't be referenced uniless the full packet scheduler layer is enabled. Reported by Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-21 09:13:01 +08:00
#ifdef CONFIG_NET_SCHED
net: sched: convert qdisc linked list to hashtable Convert the per-device linked list into a hashtable. The primary motivation for this change is that currently, we're not tracking all the qdiscs in hierarchy (e.g. excluding default qdiscs), as the lookup performed over the linked list by qdisc_match_from_root() is rather expensive. The ultimate goal is to get rid of hidden qdiscs completely, which will bring much more determinism in user experience. Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-10 17:05:15 +08:00
qdisc_hash_del(qdisc);
pkt_sched: Fix qdisc list locking Since some qdiscs call qdisc_tree_decrease_qlen() (so qdisc_lookup()) without rtnl_lock(), adding and deleting from a qdisc list needs additional locking. This patch adds global spinlock qdisc_list_lock and wrapper functions for modifying the list. It is considered as a temporary solution until hfsc_dequeue(), netem_dequeue() and tbf_dequeue() (or qdisc_tree_decrease_qlen()) are redone. With feedback from Herbert Xu and David S. Miller. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-22 18:24:05 +08:00
net_sched: RCU conversion of stab This patch converts stab qdisc management to RCU, so that we can perform the qdisc_calculate_pkt_len() call before getting qdisc lock. This shortens the lock's held time in __dev_xmit_skb(). This permits more qdiscs to get TCQ_F_CAN_BYPASS status, avoiding lot of cache misses and so reducing latencies. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Patrick McHardy <kaber@trash.net> CC: Jesper Dangaard Brouer <hawk@diku.dk> CC: Jarek Poplawski <jarkao2@gmail.com> CC: Jamal Hadi Salim <hadi@cyberus.ca> CC: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-20 11:48:19 +08:00
qdisc_put_stab(rtnl_dereference(qdisc->stab));
pkt_sched: Fix build with NET_SCHED disabled. The stab bits can't be referenced uniless the full packet scheduler layer is enabled. Reported by Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-21 09:13:01 +08:00
#endif
net_sched: gen_estimator: complete rewrite of rate estimators 1) Old code was hard to maintain, due to complex lock chains. (We probably will be able to remove some kfree_rcu() in callers) 2) Using a single timer to update all estimators does not scale. 3) Code was buggy on 32bit kernel (WRITE_ONCE() on 64bit quantity is not supposed to work well) In this rewrite : - I removed the RB tree that had to be scanned in gen_estimator_active(). qdisc dumps should be much faster. - Each estimator has its own timer. - Estimations are maintained in net_rate_estimator structure, instead of dirtying the qdisc. Minor, but part of the simplification. - Reading the estimator uses RCU and a seqcount to provide proper support for 32bit kernels. - We reduce memory need when estimators are not used, since we store a pointer, instead of the bytes/packets counters. - xt_rateest_mt() no longer has to grab a spinlock. (In the future, xt_rateest_tg() could be switched to per cpu counters) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-05 01:48:16 +08:00
gen_kill_estimator(&qdisc->rate_est);
pkt_sched: Perform bulk of qdisc destruction in RCU. This allows less strict control of access to the qdisc attached to a netdev_queue. It is even allowed to enqueue into a qdisc which is in the process of being destroyed. The RCU handler will toss out those packets. We will need this to handle sharing of a qdisc amongst multiple TX queues. In such a setup the lock has to be shared, so will be inside of the qdisc itself. At which point the netdev_queue lock cannot be used to hard synchronize access to the ->qdisc pointer. One operation we have to keep inside of qdisc_destroy() is the list deletion. It is the only piece of state visible after the RCU quiesce period, so we have to undo it early and under the appropriate locking. The operations in the RCU handler do not need any looking because the qdisc tree is no longer visible to anything at that point. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:47:45 +08:00
if (ops->reset)
ops->reset(qdisc);
if (ops->destroy)
ops->destroy(qdisc);
module_put(ops->owner);
dev_put(qdisc_dev(qdisc));
net: sched: explicit locking in gso_cpu fallback This work is preparing the qdisc layer to support egress lockless qdiscs. If we are running the egress qdisc lockless in the case we overrun the netdev, for whatever reason, the netdev returns a busy error code and the skb is parked on the gso_skb pointer. With many cores all hitting this case at once its possible to have multiple sk_buffs here so we turn gso_skb into a queue. This should be the edge case and if we see this frequently then the netdev/qdisc layer needs to back off. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:55:45 +08:00
skb_queue_walk_safe(&qdisc->gso_skb, skb, tmp) {
__skb_unlink(skb, &qdisc->gso_skb);
kfree_skb_list(skb);
}
net: sched: use skb list for skb_bad_tx Similar to how gso is handled use skb list for skb_bad_tx this is required with lockless qdiscs because we may have multiple cores attempting to push skbs into skb_bad_tx concurrently Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:23 +08:00
skb_queue_walk_safe(&qdisc->skb_bad_txq, skb, tmp) {
__skb_unlink(skb, &qdisc->skb_bad_txq);
kfree_skb_list(skb);
}
net: sched: extend Qdisc with rcu Currently, Qdisc API functions assume that users have rtnl lock taken. To implement rtnl unlocked classifiers update interface, Qdisc API must be extended with functions that do not require rtnl lock. Extend Qdisc structure with rcu. Implement special version of put function qdisc_put_unlocked() that is called without rtnl lock taken. This function only takes rtnl lock if Qdisc reference counter reached zero and is intended to be used as optimization. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:51 +08:00
call_rcu(&qdisc->rcu, qdisc_free_cb);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
net: sched: rename qdisc_destroy() to qdisc_put() Current implementation of qdisc_destroy() decrements Qdisc reference counter and only actually destroy Qdisc if reference counter value reached zero. Rename qdisc_destroy() to qdisc_put() in order for it to better describe the way in which this function currently implemented and used. Extract code that deallocates Qdisc into new private qdisc_destroy() function. It is intended to be shared between regular qdisc_put() and its unlocked version that is introduced in next patch in this series. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:50 +08:00
void qdisc_put(struct Qdisc *qdisc)
{
if (qdisc->flags & TCQ_F_BUILTIN ||
!refcount_dec_and_test(&qdisc->refcnt))
return;
qdisc_destroy(qdisc);
}
EXPORT_SYMBOL(qdisc_put);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net: sched: extend Qdisc with rcu Currently, Qdisc API functions assume that users have rtnl lock taken. To implement rtnl unlocked classifiers update interface, Qdisc API must be extended with functions that do not require rtnl lock. Extend Qdisc structure with rcu. Implement special version of put function qdisc_put_unlocked() that is called without rtnl lock taken. This function only takes rtnl lock if Qdisc reference counter reached zero and is intended to be used as optimization. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:51 +08:00
/* 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;
qdisc_destroy(qdisc);
rtnl_unlock();
}
EXPORT_SYMBOL(qdisc_put_unlocked);
net_sched: move dev_graft_qdisc() to sch_generic.c It will be used in a following patch by the multiqueue qdisc. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-04 14:41:20 +08:00
/* Attach toplevel qdisc to device queue. */
struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
struct Qdisc *qdisc)
{
struct Qdisc *oqdisc = 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;
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 16:06:09 +08:00
EXPORT_SYMBOL(dev_graft_qdisc);
net_sched: move dev_graft_qdisc() to sch_generic.c It will be used in a following patch by the multiqueue qdisc. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-04 14:41:20 +08:00
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
static void attach_one_default_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_unused)
{
net: sched: simplify attach_one_default_qdisc() Now that noqueue qdisc can be attached just like any other qdisc, no special treatment is necessary anymore when attaching it as default qdisc. This change has the added benefit that 'tc qdisc show' prints noqueue instead of nothing for devices defaulting to noqueue. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-28 03:21:39 +08:00
struct Qdisc *qdisc;
const struct Qdisc_ops *ops = default_qdisc_ops;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
net: sched: simplify attach_one_default_qdisc() Now that noqueue qdisc can be attached just like any other qdisc, no special treatment is necessary anymore when attaching it as default qdisc. This change has the added benefit that 'tc qdisc show' prints noqueue instead of nothing for devices defaulting to noqueue. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-28 03:21:39 +08:00
if (dev->priv_flags & IFF_NO_QUEUE)
ops = &noqueue_qdisc_ops;
net: sch: api: add extack support in qdisc_create_dflt This patch adds extack support for the function qdisc_create_dflt which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_create_dflt failed. The function qdisc_create_dflt will also call an init callback which can fail by any per-qdisc specific handling. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:21 +08:00
qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL);
net: sched: simplify attach_one_default_qdisc() Now that noqueue qdisc can be attached just like any other qdisc, no special treatment is necessary anymore when attaching it as default qdisc. This change has the added benefit that 'tc qdisc show' prints noqueue instead of nothing for devices defaulting to noqueue. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-28 03:21:39 +08:00
if (!qdisc) {
netdev_info(dev, "activation failed\n");
return;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
}
net: sched: simplify attach_one_default_qdisc() Now that noqueue qdisc can be attached just like any other qdisc, no special treatment is necessary anymore when attaching it as default qdisc. This change has the added benefit that 'tc qdisc show' prints noqueue instead of nothing for devices defaulting to noqueue. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-28 03:21:39 +08:00
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 12:08:51 +08:00
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
dev_queue->qdisc_sleeping = qdisc;
}
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
static void attach_default_qdiscs(struct net_device *dev)
{
struct netdev_queue *txq;
struct Qdisc *qdisc;
txq = netdev_get_tx_queue(dev, 0);
net: sch_generic: react upon IFF_NO_QUEUE flag Handle IFF_NO_QUEUE as alternative to tx_queue_len being zero. Signed-off-by: Phil Sutter <phil@nwl.cc> Acked-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-14 01:01:07 +08:00
if (!netif_is_multiqueue(dev) ||
dev->priv_flags & IFF_NO_QUEUE) {
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
dev->qdisc = txq->qdisc_sleeping;
net_sched: fix a refcount_t issue with noop_qdisc syzkaller reported a refcount_t warning [1] Issue here is that noop_qdisc refcnt was never really considered as a true refcount, since qdisc_destroy() found TCQ_F_BUILTIN set : if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_test(&qdisc->refcnt))) return; Meaning that all atomic_inc() we did on noop_qdisc.refcnt were not really needed, but harmless until refcount_t came. To fix this problem, we simply need to not increment noop_qdisc.refcnt, since we never decrement it. [1] refcount_t: increment on 0; use-after-free. ------------[ cut here ]------------ WARNING: CPU: 0 PID: 21754 at lib/refcount.c:152 refcount_inc+0x47/0x50 lib/refcount.c:152 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 21754 Comm: syz-executor7 Not tainted 4.13.0-rc6+ #20 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:16 [inline] dump_stack+0x194/0x257 lib/dump_stack.c:52 panic+0x1e4/0x417 kernel/panic.c:180 __warn+0x1c4/0x1d9 kernel/panic.c:541 report_bug+0x211/0x2d0 lib/bug.c:183 fixup_bug+0x40/0x90 arch/x86/kernel/traps.c:190 do_trap_no_signal arch/x86/kernel/traps.c:224 [inline] do_trap+0x260/0x390 arch/x86/kernel/traps.c:273 do_error_trap+0x120/0x390 arch/x86/kernel/traps.c:310 do_invalid_op+0x1b/0x20 arch/x86/kernel/traps.c:323 invalid_op+0x1e/0x30 arch/x86/entry/entry_64.S:846 RIP: 0010:refcount_inc+0x47/0x50 lib/refcount.c:152 RSP: 0018:ffff8801c43477a0 EFLAGS: 00010282 RAX: 000000000000002b RBX: ffffffff86093c14 RCX: 0000000000000000 RDX: 000000000000002b RSI: ffffffff8159314e RDI: ffffed0038868ee8 RBP: ffff8801c43477a8 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff86093ac0 R13: 0000000000000001 R14: ffff8801d0f3bac0 R15: dffffc0000000000 attach_default_qdiscs net/sched/sch_generic.c:792 [inline] dev_activate+0x7d3/0xaa0 net/sched/sch_generic.c:833 __dev_open+0x227/0x330 net/core/dev.c:1380 __dev_change_flags+0x695/0x990 net/core/dev.c:6726 dev_change_flags+0x88/0x140 net/core/dev.c:6792 dev_ifsioc+0x5a6/0x930 net/core/dev_ioctl.c:256 dev_ioctl+0x2bc/0xf90 net/core/dev_ioctl.c:554 sock_do_ioctl+0x94/0xb0 net/socket.c:968 sock_ioctl+0x2c2/0x440 net/socket.c:1058 vfs_ioctl fs/ioctl.c:45 [inline] do_vfs_ioctl+0x1b1/0x1520 fs/ioctl.c:685 SYSC_ioctl fs/ioctl.c:700 [inline] SyS_ioctl+0x8f/0xc0 fs/ioctl.c:691 Fixes: 7b9364050246 ("net, sched: convert Qdisc.refcnt from atomic_t to refcount_t") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Reshetova, Elena <elena.reshetova@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-25 12:12:28 +08:00
qdisc_refcount_inc(dev->qdisc);
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
} else {
net: sch: api: add extack support in qdisc_create_dflt This patch adds extack support for the function qdisc_create_dflt which is a common used function in the tc subsystem. Callers which are interested in the receiving error can assign extack to get a more detailed information why qdisc_create_dflt failed. The function qdisc_create_dflt will also call an init callback which can fail by any per-qdisc specific handling. Cc: David Ahern <dsahern@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Alexander Aring <aring@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 01:35:21 +08:00
qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL);
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
if (qdisc) {
dev->qdisc = qdisc;
pkt_sched: set root qdisc before change() in attach_default_qdiscs() After commit 95dc19299f74 ("pkt_sched: give visibility to mq slave qdiscs") we call disc_list_add() while the device qdisc might be the noop_qdisc one. This shows up as duplicates in "tc qdisc show", as all inactive devices point to noop_qdisc. Fix this by setting dev->qdisc to the new qdisc before calling ops->change() in attach_default_qdiscs() Add a WARN_ON_ONCE() to catch any future similar problem. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-12-13 07:41:56 +08:00
qdisc->ops->attach(qdisc);
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
}
}
net: sched: convert qdisc linked list to hashtable Convert the per-device linked list into a hashtable. The primary motivation for this change is that currently, we're not tracking all the qdiscs in hierarchy (e.g. excluding default qdiscs), as the lookup performed over the linked list by qdisc_match_from_root() is rather expensive. The ultimate goal is to get rid of hidden qdiscs completely, which will bring much more determinism in user experience. Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-10 17:05:15 +08:00
#ifdef CONFIG_NET_SCHED
net_sched: check noop_qdisc before qdisc_hash_add() Dmitry reported a crash when injecting faults in attach_one_default_qdisc() and dev->qdisc is still a noop_disc, the check before qdisc_hash_add() fails to catch it because it tests NULL. We should test against noop_qdisc since it is the default qdisc at this point. Fixes: 59cc1f61f09c ("net: sched: convert qdisc linked list to hashtable") Reported-by: Dmitry Vyukov <dvyukov@google.com> Cc: Jiri Kosina <jkosina@suse.cz> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-04-05 09:51:30 +08:00
if (dev->qdisc != &noop_qdisc)
net: sched: make default fifo qdiscs appear in the dump The original reason [1] for having hidden qdiscs (potential scalability issues in qdisc_match_from_root() with single linked list in case of large amount of qdiscs) has been invalidated by 59cc1f61f0 ("net: sched: convert qdisc linked list to hashtable"). This allows us for bringing more clarity and determinism into the dump by making default pfifo qdiscs visible. We're not turning this on by default though, at it was deemed [2] too intrusive / unnecessary change of default behavior towards userspace. Instead, TCA_DUMP_INVISIBLE netlink attribute is introduced, which allows applications to request complete qdisc hierarchy dump, including the ones that have always been implicit/invisible. Singleton noop_qdisc stays invisible, as teaching the whole infrastructure about singletons would require quite some surgery with very little gain (seeing no qdisc or seeing noop qdisc in the dump is probably setting the same user expectation). [1] http://lkml.kernel.org/r/1460732328.10638.74.camel@edumazet-glaptop3.roam.corp.google.com [2] http://lkml.kernel.org/r/20161021.105935.1907696543877061916.davem@davemloft.net Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-08 23:03:32 +08:00
qdisc_hash_add(dev->qdisc, false);
net: sched: convert qdisc linked list to hashtable Convert the per-device linked list into a hashtable. The primary motivation for this change is that currently, we're not tracking all the qdiscs in hierarchy (e.g. excluding default qdiscs), as the lookup performed over the linked list by qdisc_match_from_root() is rather expensive. The ultimate goal is to get rid of hidden qdiscs completely, which will bring much more determinism in user experience. Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jiri Kosina <jkosina@suse.cz> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-08-10 17:05:15 +08:00
#endif
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
}
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
static void transition_one_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_need_watchdog)
{
pkt_sched: Kill netdev_queue lock. We can simply use the qdisc->q.lock for all of the qdisc tree synchronization. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:53:03 +08:00
struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
int *need_watchdog_p = _need_watchdog;
pkt_sched: Add 'deactivated' state. This new state lets dev_deactivate() mark a qdisc as having been deactivated. dev_queue_xmit() and ing_filter() check for this bit and do not try to process the qdisc if the bit is set. dev_deactivate() polls the qdisc after setting the bit, waiting for both __QDISC_STATE_RUNNING and __QDISC_STATE_SCHED to clear. This isn't perfect yet, but subsequent changesets will make it so. This part is just one piece of the puzzle. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-18 12:51:03 +08:00
if (!(new_qdisc->flags & TCQ_F_BUILTIN))
clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state);
pkt_sched: Kill netdev_queue lock. We can simply use the qdisc->q.lock for all of the qdisc tree synchronization. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:53:03 +08:00
rcu_assign_pointer(dev_queue->qdisc, new_qdisc);
net: sched: simplify attach_one_default_qdisc() Now that noqueue qdisc can be attached just like any other qdisc, no special treatment is necessary anymore when attaching it as default qdisc. This change has the added benefit that 'tc qdisc show' prints noqueue instead of nothing for devices defaulting to noqueue. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-28 03:21:39 +08:00
if (need_watchdog_p) {
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
dev_queue->trans_start = 0;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
*need_watchdog_p = 1;
net: tx scalability works : trans_start struct net_device trans_start field is a hot spot on SMP and high performance devices, particularly multi queues ones, because every transmitter dirties it. Is main use is tx watchdog and bonding alive checks. But as most devices dont use NETIF_F_LLTX, we have to lock a netdev_queue before calling their ndo_start_xmit(). So it makes sense to move trans_start from net_device to netdev_queue. Its update will occur on a already present (and in exclusive state) cache line, for free. We can do this transition smoothly. An old driver continue to update dev->trans_start, while an updated one updates txq->trans_start. Further patches could also put tx_bytes/tx_packets counters in netdev_queue to avoid dirtying dev->stats (vlan device comes to mind) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-05-18 11:55:16 +08:00
}
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
void dev_activate(struct net_device *dev)
{
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
int need_watchdog;
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* No queueing discipline is attached to device;
qdisc: allow setting default queuing discipline By default, the pfifo_fast queue discipline has been used by default for all devices. But we have better choices now. This patch allow setting the default queueing discipline with sysctl. This allows easy use of better queueing disciplines on all devices without having to use tc qdisc scripts. It is intended to allow an easy path for distributions to make fq_codel or sfq the default qdisc. This patch also makes pfifo_fast more of a first class qdisc, since it is now possible to manually override the default and explicitly use pfifo_fast. The behavior for systems who do not use the sysctl is unchanged, they still get pfifo_fast Also removes leftover random # in sysctl net core. Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-28 07:19:08 +08:00
* create default one for devices, which need queueing
* and noqueue_qdisc for virtual interfaces
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
*/
net_sched: add classful multiqueue dummy scheduler This patch adds a classful dummy scheduler which can be used as root qdisc for multiqueue devices and exposes each device queue as a child class. This allows to address queues individually and graft them similar to regular classes. Additionally it presents an accumulated view of the statistics of all real root qdiscs in the dummy root. Two new callbacks are added to the qdisc_ops and qdisc_class_ops: - cl_ops->select_queue selects the tx queue number for new child classes. - qdisc_ops->attach() overrides root qdisc device grafting to attach non-shared qdiscs to the queues. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-06 16:58:51 +08:00
if (dev->qdisc == &noop_qdisc)
attach_default_qdiscs(dev);
net_sched: reintroduce dev->qdisc for use by sch_api Currently the multiqueue integration with the qdisc API suffers from a few problems: - with multiple queues, all root qdiscs use the same handle. This means they can't be exposed to userspace in a backwards compatible fashion. - all API operations always refer to queue number 0. Newly created qdiscs are automatically shared between all queues, its not possible to address individual queues or restore multiqueue behaviour once a shared qdisc has been attached. - Dumps only contain the root qdisc of queue 0, in case of non-shared qdiscs this means the statistics are incomplete. This patch reintroduces dev->qdisc, which points to the (single) root qdisc from userspace's point of view. Currently it either points to the first (non-shared) default qdisc, or a qdisc shared between all queues. The following patches will introduce a classful dummy qdisc, which will be used as root qdisc and contain the per-queue qdiscs as children. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-04 14:41:18 +08:00
[NET]: Disable queueing when carrier is lost. Some network drivers call netif_stop_queue() when detecting loss of carrier. This leads to packets being queued up at the qdisc level for an unbound period of time. In order to prevent this effect, the core networking stack will now cease to queue packets for any device, that is operationally down (i.e. the queue is flushed and disabled). Signed-off-by: Tommy S. Christensen <tommy.christensen@tpack.net> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-05-04 07:18:52 +08:00
if (!netif_carrier_ok(dev))
/* Delay activation until next carrier-on event */
return;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
need_watchdog = 0;
netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog);
net: dynamic ingress_queue allocation ingress being not used very much, and net_device->ingress_queue being quite a big object (128 or 256 bytes), use a dynamic allocation if needed (tc qdisc add dev eth0 ingress ...) dev_ingress_queue(dev) helper should be used only with RTNL taken. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-02 14:11:55 +08:00
if (dev_ingress_queue(dev))
transition_one_qdisc(dev, dev_ingress_queue(dev), NULL);
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
if (need_watchdog) {
treewide: replace dev->trans_start update with helper Replace all trans_start updates with netif_trans_update helper. change was done via spatch: struct net_device *d; @@ - d->trans_start = jiffies + netif_trans_update(d) Compile tested only. Cc: user-mode-linux-devel@lists.sourceforge.net Cc: linux-xtensa@linux-xtensa.org Cc: linux1394-devel@lists.sourceforge.net Cc: linux-rdma@vger.kernel.org Cc: netdev@vger.kernel.org Cc: MPT-FusionLinux.pdl@broadcom.com Cc: linux-scsi@vger.kernel.org Cc: linux-can@vger.kernel.org Cc: linux-parisc@vger.kernel.org Cc: linux-omap@vger.kernel.org Cc: linux-hams@vger.kernel.org Cc: linux-usb@vger.kernel.org Cc: linux-wireless@vger.kernel.org Cc: linux-s390@vger.kernel.org Cc: devel@driverdev.osuosl.org Cc: b.a.t.m.a.n@lists.open-mesh.org Cc: linux-bluetooth@vger.kernel.org Signed-off-by: Florian Westphal <fw@strlen.de> Acked-by: Felipe Balbi <felipe.balbi@linux.intel.com> Acked-by: Mugunthan V N <mugunthanvnm@ti.com> Acked-by: Antonio Quartulli <a@unstable.cc> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-05-03 22:33:13 +08:00
netif_trans_update(dev);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dev_watchdog_up(dev);
}
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
}
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 16:06:09 +08:00
EXPORT_SYMBOL(dev_activate);
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
static void dev_deactivate_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc_default)
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
{
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
struct Qdisc *qdisc_default = _qdisc_default;
netdev: Move gso_skb into netdev_queue. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 14:10:33 +08:00
struct Qdisc *qdisc;
net: qdisc: use rcu prefix and silence sparse warnings Add __rcu notation to qdisc handling by doing this we can make smatch output more legible. And anyways some of the cases should be using rcu_dereference() see qdisc_all_tx_empty(), qdisc_tx_chainging(), and so on. Also *wake_queue() API is commonly called from driver timer routines without rcu lock or rtnl lock. So I added rcu_read_lock() blocks around netif_wake_subqueue and netif_tx_wake_queue. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-13 11:04:52 +08:00
qdisc = rtnl_dereference(dev_queue->qdisc);
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
if (qdisc) {
sched: replace __QDISC_STATE_RUNNING bit with a spin lock So that we can use lockdep on it. The newly introduced sequence lock has the same scope of busylock, so it shares the same lockdep annotation, but it's only used for NOLOCK qdiscs. With this changeset we acquire such lock in the control path around flushing operation (qdisc reset), to allow more NOLOCK qdisc perf improvement in the next patch. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 22:24:36 +08:00
bool nolock = qdisc->flags & TCQ_F_NOLOCK;
if (nolock)
spin_lock_bh(&qdisc->seqlock);
pkt_sched: Kill netdev_queue lock. We can simply use the qdisc->q.lock for all of the qdisc tree synchronization. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:53:03 +08:00
spin_lock_bh(qdisc_lock(qdisc));
pkt_sched: Add 'deactivated' state. This new state lets dev_deactivate() mark a qdisc as having been deactivated. dev_queue_xmit() and ing_filter() check for this bit and do not try to process the qdisc if the bit is set. dev_deactivate() polls the qdisc after setting the bit, waiting for both __QDISC_STATE_RUNNING and __QDISC_STATE_SCHED to clear. This isn't perfect yet, but subsequent changesets will make it so. This part is just one piece of the puzzle. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-18 12:51:03 +08:00
if (!(qdisc->flags & TCQ_F_BUILTIN))
set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
pkt_sched: Use rcu_assign_pointer() to change dev_queue->qdisc These pointers are RCU protected, so proper primitives should be used. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-27 17:22:07 +08:00
rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
qdisc_reset(qdisc);
pkt_sched: Move gso_skb into Qdisc. We liberate any dangling gso_skb during qdisc destruction. It really only matters for the root qdisc. But when qdiscs can be shared by multiple netdev_queue objects, we can't have the gso_skb in the netdev_queue any more. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 11:14:35 +08:00
pkt_sched: Kill netdev_queue lock. We can simply use the qdisc->q.lock for all of the qdisc tree synchronization. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:53:03 +08:00
spin_unlock_bh(qdisc_lock(qdisc));
sched: replace __QDISC_STATE_RUNNING bit with a spin lock So that we can use lockdep on it. The newly introduced sequence lock has the same scope of busylock, so it shares the same lockdep annotation, but it's only used for NOLOCK qdiscs. With this changeset we acquire such lock in the control path around flushing operation (qdisc reset), to allow more NOLOCK qdisc perf improvement in the next patch. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 22:24:36 +08:00
if (nolock)
spin_unlock_bh(&qdisc->seqlock);
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
pkt_sched: Simplify dev_deactivate() polling loop. The condition under which the previous qdisc has no more references after we've attached &noop_qdisc is that both RUNNING and SCHED are both seen clear while holding the root lock. So just make specifically that check in the polling loop, instead of this overly complex "check without then check with lock held" sequence. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-18 12:58:07 +08:00
static bool some_qdisc_is_busy(struct net_device *dev)
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *dev_queue;
pkt_sched: Add and use qdisc_root() and qdisc_root_lock(). When code wants to lock the qdisc tree state, the logic operation it's doing is locking the top-level qdisc that sits of the root of the netdev_queue. Add qdisc_root_lock() to represent this and convert the easiest cases. In order for this to work out in all cases, we have to hook up the noop_qdisc to a dummy netdev_queue. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 16:42:40 +08:00
spinlock_t *root_lock;
pkt_sched: Make QDISC_RUNNING a qdisc state. Currently it is associated with a netdev_queue, but when we have qdisc sharing that no longer makes any sense. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-16 15:56:32 +08:00
struct Qdisc *q;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
int val;
dev_queue = netdev_get_tx_queue(dev, i);
pkt_sched: Fix queue quiescence testing in dev_deactivate(). Based upon discussions with Jarek P. and Herbert Xu. First, we're testing the wrong qdisc. We just reset the device queue qdiscs to &noop_qdisc and checking it's state is completely pointless here. We want to wait until the previous qdisc that was sitting at the ->qdisc pointer is not busy any more. And that would be ->qdisc_sleeping. Because of how we propagate the samples qdisc pointer down into qdisc_run and friends via per-cpu ->output_queue and netif_schedule, we have to wait also for the __QDISC_STATE_SCHED bit to clear as well. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-14 06:18:38 +08:00
q = dev_queue->qdisc_sleeping;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
sched: manipulate __QDISC_STATE_RUNNING in qdisc_run_* helpers Currently NOLOCK qdiscs pay a measurable overhead to atomically manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per packet in the uncontended scenario with packet rate below the line rate: on packed dequeue and on the next, failing dequeue attempt. This changeset moves the bit manipulation into the qdisc_run_{begin,end} helpers, so that the bit is now flipped only once per packet, with measurable performance improvement in the uncontended scenario. This also allows simplifying the qdisc teardown code path - since qdisc_is_running() is now effective for each qdisc type - and avoid a possible race between qdisc_run() and dev_deactivate_many(), as now the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy dequeuing packets. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 16:50:31 +08:00
root_lock = qdisc_lock(q);
spin_lock_bh(root_lock);
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
sched: manipulate __QDISC_STATE_RUNNING in qdisc_run_* helpers Currently NOLOCK qdiscs pay a measurable overhead to atomically manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per packet in the uncontended scenario with packet rate below the line rate: on packed dequeue and on the next, failing dequeue attempt. This changeset moves the bit manipulation into the qdisc_run_{begin,end} helpers, so that the bit is now flipped only once per packet, with measurable performance improvement in the uncontended scenario. This also allows simplifying the qdisc teardown code path - since qdisc_is_running() is now effective for each qdisc type - and avoid a possible race between qdisc_run() and dev_deactivate_many(), as now the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy dequeuing packets. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 16:50:31 +08:00
val = (qdisc_is_running(q) ||
test_bit(__QDISC_STATE_SCHED, &q->state));
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
sched: manipulate __QDISC_STATE_RUNNING in qdisc_run_* helpers Currently NOLOCK qdiscs pay a measurable overhead to atomically manipulate the __QDISC_STATE_RUNNING. Such bit is flipped twice per packet in the uncontended scenario with packet rate below the line rate: on packed dequeue and on the next, failing dequeue attempt. This changeset moves the bit manipulation into the qdisc_run_{begin,end} helpers, so that the bit is now flipped only once per packet, with measurable performance improvement in the uncontended scenario. This also allows simplifying the qdisc teardown code path - since qdisc_is_running() is now effective for each qdisc type - and avoid a possible race between qdisc_run() and dev_deactivate_many(), as now the some_qdisc_is_busy() can properly detect NOLOCK qdiscs being busy dequeuing packets. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-15 16:50:31 +08:00
spin_unlock_bh(root_lock);
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
if (val)
return true;
}
return false;
}
net: sched: drop qdisc_reset from dev_graft_qdisc In qdisc_graft_qdisc a "new" qdisc is attached and the 'qdisc_destroy' operation is called on the old qdisc. The destroy operation will wait a rcu grace period and call qdisc_rcu_free(). At which point gso_cpu_skb is free'd along with all stats so no need to zero stats and gso_cpu_skb from the graft operation itself. Further after dropping the qdisc locks we can not continue to call qdisc_reset before waiting an rcu grace period so that the qdisc is detached from all cpus. By removing the qdisc_reset() here we get the correct property of waiting an rcu grace period and letting the qdisc_destroy operation clean up the qdisc correctly. Note, a refcnt greater than 1 would cause the destroy operation to be aborted however if this ever happened the reference to the qdisc would be lost and we would have a memory leak. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:04 +08:00
static void dev_qdisc_reset(struct net_device *dev,
struct netdev_queue *dev_queue,
void *none)
{
struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
if (qdisc)
qdisc_reset(qdisc);
}
net: avoid synchronize_rcu() in dev_deactivate_many dev_deactivate_many() issues one synchronize_rcu() call after qdiscs set to noop_qdisc. This call is here to make sure they are no outstanding qdisc-less dev_queue_xmit calls before returning to caller. But in dismantle phase, we dont have to wait, because we wont activate again the device, and we are going to wait one rcu grace period later in rollback_registered_many(). After this patch, device dismantle uses one synchronize_net() and one rcu_barrier() call only, so we have a ~30% speedup and a smaller RTNL latency. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Patrick McHardy <kaber@trash.net>, CC: Ben Greear <greearb@candelatech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-20 07:42:09 +08:00
/**
* 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.
*/
net: factorize sync-rcu call in unregister_netdevice_many Add dev_close_many and dev_deactivate_many to factorize another sync-rcu operation on the netdevice unregister path. $ modprobe dummy numdummies=10000 $ ip link set dev dummy* up $ time rmmod dummy Without the patch With the patch real 0m 24.63s real 0m 5.15s user 0m 0.00s user 0m 0.00s sys 0m 6.05s sys 0m 5.14s Signed-off-by: Octavian Purdila <opurdila@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-13 20:44:07 +08:00
void dev_deactivate_many(struct list_head *head)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
net: factorize sync-rcu call in unregister_netdevice_many Add dev_close_many and dev_deactivate_many to factorize another sync-rcu operation on the netdevice unregister path. $ modprobe dummy numdummies=10000 $ ip link set dev dummy* up $ time rmmod dummy Without the patch With the patch real 0m 24.63s real 0m 5.15s user 0m 0.00s user 0m 0.00s sys 0m 6.05s sys 0m 5.14s Signed-off-by: Octavian Purdila <opurdila@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-13 20:44:07 +08:00
struct net_device *dev;
[NET_SCHED]: Avoid requeue warning on dev_deactivate When we relinquish queue_lock in qdisc_restart and then retake it for requeueing, we might race against dev_deactivate and end up requeueing onto noop_qdisc. This causes a warning to be printed. This patch fixes this by checking this before we requeue. As an added bonus, we can remove the same check in __qdisc_run which was added to prevent dev->gso_skb from being requeued when we're shutting down. Even though we've had to add a new conditional in its place, it's better because it only happens on requeues rather than every single time that qdisc_run is called. For this to work we also need to move the clearing of gso_skb up in dev_deactivate as now qdisc_restart can occur even after we wait for __LINK_STATE_QDISC_RUNNING to clear (but it won't do anything as long as the queue and gso_skb is already clear). Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-11 05:12:47 +08:00
net: Separate the close_list and the unreg_list v2 Separate the unreg_list and the close_list in dev_close_many preventing dev_close_many from permuting the unreg_list. The permutations of the unreg_list have resulted in cases where the loopback device is accessed it has been freed in code such as dst_ifdown. Resulting in subtle memory corruption. This is the second bug from sharing the storage between the close_list and the unreg_list. The issues that crop up with sharing are apparently too subtle to show up in normal testing or usage, so let's forget about being clever and use two separate lists. v2: Make all callers pass in a close_list to dev_close_many Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-06 10:26:05 +08:00
list_for_each_entry(dev, head, close_list) {
net: factorize sync-rcu call in unregister_netdevice_many Add dev_close_many and dev_deactivate_many to factorize another sync-rcu operation on the netdevice unregister path. $ modprobe dummy numdummies=10000 $ ip link set dev dummy* up $ time rmmod dummy Without the patch With the patch real 0m 24.63s real 0m 5.15s user 0m 0.00s user 0m 0.00s sys 0m 6.05s sys 0m 5.14s Signed-off-by: Octavian Purdila <opurdila@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-13 20:44:07 +08:00
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);
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net: avoid synchronize_rcu() in dev_deactivate_many dev_deactivate_many() issues one synchronize_rcu() call after qdiscs set to noop_qdisc. This call is here to make sure they are no outstanding qdisc-less dev_queue_xmit calls before returning to caller. But in dismantle phase, we dont have to wait, because we wont activate again the device, and we are going to wait one rcu grace period later in rollback_registered_many(). After this patch, device dismantle uses one synchronize_net() and one rcu_barrier() call only, so we have a ~30% speedup and a smaller RTNL latency. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> CC: Patrick McHardy <kaber@trash.net>, CC: Ben Greear <greearb@candelatech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-05-20 07:42:09 +08:00
/* Wait for outstanding qdisc-less dev_queue_xmit calls.
* This is avoided if all devices are in dismantle phase :
* Caller will call synchronize_net() for us
*/
net: sched: drop qdisc_reset from dev_graft_qdisc In qdisc_graft_qdisc a "new" qdisc is attached and the 'qdisc_destroy' operation is called on the old qdisc. The destroy operation will wait a rcu grace period and call qdisc_rcu_free(). At which point gso_cpu_skb is free'd along with all stats so no need to zero stats and gso_cpu_skb from the graft operation itself. Further after dropping the qdisc locks we can not continue to call qdisc_reset before waiting an rcu grace period so that the qdisc is detached from all cpus. By removing the qdisc_reset() here we get the correct property of waiting an rcu grace period and letting the qdisc_destroy operation clean up the qdisc correctly. Note, a refcnt greater than 1 would cause the destroy operation to be aborted however if this ever happened the reference to the qdisc would be lost and we would have a memory leak. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:04 +08:00
synchronize_net();
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[NET]: Prevent transmission after dev_deactivate The dev_deactivate function has bit-rotted since the introduction of lockless drivers. In particular, the spin_unlock_wait call at the end has no effect on the xmit routine of lockless drivers. With a little bit of work, we can make it much more useful by providing the guarantee that when it returns, no more calls to the xmit routine of the underlying driver will be made. The idea is simple. There are two entry points in to the xmit routine. The first comes from dev_queue_xmit. That one is easily stopped by using synchronize_rcu. This works because we set the qdisc to noop_qdisc before the synchronize_rcu call. That in turn causes all subsequent packets sent to dev_queue_xmit to be dropped. The synchronize_rcu call also ensures all outstanding calls leave their critical section. The other entry point is from qdisc_run. Since we now have a bit that indicates whether it's running, all we have to do is to wait until the bit is off. I've removed the loop to wait for __LINK_STATE_SCHED to clear. This is useless because netif_wake_queue can cause it to be set again. It is also harmless because we've disarmed qdisc_run. I've also removed the spin_unlock_wait on xmit_lock because its only purpose of making sure that all outstanding xmit_lock holders have exited is also given by dev_watchdog_down. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 17:28:18 +08:00
/* Wait for outstanding qdisc_run calls. */
net: sched: drop qdisc_reset from dev_graft_qdisc In qdisc_graft_qdisc a "new" qdisc is attached and the 'qdisc_destroy' operation is called on the old qdisc. The destroy operation will wait a rcu grace period and call qdisc_rcu_free(). At which point gso_cpu_skb is free'd along with all stats so no need to zero stats and gso_cpu_skb from the graft operation itself. Further after dropping the qdisc locks we can not continue to call qdisc_reset before waiting an rcu grace period so that the qdisc is detached from all cpus. By removing the qdisc_reset() here we get the correct property of waiting an rcu grace period and letting the qdisc_destroy operation clean up the qdisc correctly. Note, a refcnt greater than 1 would cause the destroy operation to be aborted however if this ever happened the reference to the qdisc would be lost and we would have a memory leak. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:04 +08:00
list_for_each_entry(dev, head, close_list) {
net: factorize sync-rcu call in unregister_netdevice_many Add dev_close_many and dev_deactivate_many to factorize another sync-rcu operation on the netdevice unregister path. $ modprobe dummy numdummies=10000 $ ip link set dev dummy* up $ time rmmod dummy Without the patch With the patch real 0m 24.63s real 0m 5.15s user 0m 0.00s user 0m 0.00s sys 0m 6.05s sys 0m 5.14s Signed-off-by: Octavian Purdila <opurdila@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-13 20:44:07 +08:00
while (some_qdisc_is_busy(dev))
yield();
net: sched: drop qdisc_reset from dev_graft_qdisc In qdisc_graft_qdisc a "new" qdisc is attached and the 'qdisc_destroy' operation is called on the old qdisc. The destroy operation will wait a rcu grace period and call qdisc_rcu_free(). At which point gso_cpu_skb is free'd along with all stats so no need to zero stats and gso_cpu_skb from the graft operation itself. Further after dropping the qdisc locks we can not continue to call qdisc_reset before waiting an rcu grace period so that the qdisc is detached from all cpus. By removing the qdisc_reset() here we get the correct property of waiting an rcu grace period and letting the qdisc_destroy operation clean up the qdisc correctly. Note, a refcnt greater than 1 would cause the destroy operation to be aborted however if this ever happened the reference to the qdisc would be lost and we would have a memory leak. Signed-off-by: John Fastabend <john.fastabend@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-08 01:56:04 +08:00
/* The new qdisc is assigned at this point so we can safely
* unwind stale skb lists and qdisc statistics
*/
netdev_for_each_tx_queue(dev, dev_qdisc_reset, NULL);
if (dev_ingress_queue(dev))
dev_qdisc_reset(dev, dev_ingress_queue(dev), NULL);
}
net: factorize sync-rcu call in unregister_netdevice_many Add dev_close_many and dev_deactivate_many to factorize another sync-rcu operation on the netdevice unregister path. $ modprobe dummy numdummies=10000 $ ip link set dev dummy* up $ time rmmod dummy Without the patch With the patch real 0m 24.63s real 0m 5.15s user 0m 0.00s user 0m 0.00s sys 0m 6.05s sys 0m 5.14s Signed-off-by: Octavian Purdila <opurdila@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-13 20:44:07 +08:00
}
void dev_deactivate(struct net_device *dev)
{
LIST_HEAD(single);
net: Separate the close_list and the unreg_list v2 Separate the unreg_list and the close_list in dev_close_many preventing dev_close_many from permuting the unreg_list. The permutations of the unreg_list have resulted in cases where the loopback device is accessed it has been freed in code such as dst_ifdown. Resulting in subtle memory corruption. This is the second bug from sharing the storage between the close_list and the unreg_list. The issues that crop up with sharing are apparently too subtle to show up in normal testing or usage, so let's forget about being clever and use two separate lists. v2: Make all callers pass in a close_list to dev_close_many Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-06 10:26:05 +08:00
list_add(&dev->close_list, &single);
net: factorize sync-rcu call in unregister_netdevice_many Add dev_close_many and dev_deactivate_many to factorize another sync-rcu operation on the netdevice unregister path. $ modprobe dummy numdummies=10000 $ ip link set dev dummy* up $ time rmmod dummy Without the patch With the patch real 0m 24.63s real 0m 5.15s user 0m 0.00s user 0m 0.00s sys 0m 6.05s sys 0m 5.14s Signed-off-by: Octavian Purdila <opurdila@ixiacom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-12-13 20:44:07 +08:00
dev_deactivate_many(&single);
net: Fix more stale on-stack list_head objects. From: Eric W. Biederman <ebiederm@xmission.com> In the beginning with batching unreg_list was a list that was used only once in the lifetime of a network device (I think). Now we have calls using the unreg_list that can happen multiple times in the life of a network device like dev_deactivate and dev_close that are also using the unreg_list. In addition in unregister_netdevice_queue we also do a list_move because for devices like veth pairs it is possible that unregister_netdevice_queue will be called multiple times. So I think the change below to fix dev_deactivate which Eric D. missed will fix this problem. Now to go test that. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-21 03:49:45 +08:00
list_del(&single);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
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 16:06:09 +08:00
EXPORT_SYMBOL(dev_deactivate);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net_sched: plug in qdisc ops change_tx_queue_len Introduce a new qdisc ops ->change_tx_queue_len() so that each qdisc could decide how to implement this if it wants. Previously we simply read dev->tx_queue_len, after pfifo_fast switches to skb array, we need this API to resize the skb array when we change dev->tx_queue_len. To avoid handling race conditions with TX BH, we need to deactivate all TX queues before change the value and bring them back after we are done, this also makes implementation easier. Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-01-26 10:26:23 +08:00
static int qdisc_change_tx_queue_len(struct net_device *dev,
struct netdev_queue *dev_queue)
{
struct Qdisc *qdisc = 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;
}
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;
}
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
static void dev_init_scheduler_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
void *_qdisc)
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
{
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
struct Qdisc *qdisc = _qdisc;
net: qdisc: use rcu prefix and silence sparse warnings Add __rcu notation to qdisc handling by doing this we can make smatch output more legible. And anyways some of the cases should be using rcu_dereference() see qdisc_all_tx_empty(), qdisc_tx_chainging(), and so on. Also *wake_queue() API is commonly called from driver timer routines without rcu lock or rtnl lock. So I added rcu_read_lock() blocks around netif_wake_subqueue and netif_tx_wake_queue. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-13 11:04:52 +08:00
rcu_assign_pointer(dev_queue->qdisc, qdisc);
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
dev_queue->qdisc_sleeping = qdisc;
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
void dev_init_scheduler(struct net_device *dev)
{
net_sched: reintroduce dev->qdisc for use by sch_api Currently the multiqueue integration with the qdisc API suffers from a few problems: - with multiple queues, all root qdiscs use the same handle. This means they can't be exposed to userspace in a backwards compatible fashion. - all API operations always refer to queue number 0. Newly created qdiscs are automatically shared between all queues, its not possible to address individual queues or restore multiqueue behaviour once a shared qdisc has been attached. - Dumps only contain the root qdisc of queue 0, in case of non-shared qdiscs this means the statistics are incomplete. This patch reintroduces dev->qdisc, which points to the (single) root qdisc from userspace's point of view. Currently it either points to the first (non-shared) default qdisc, or a qdisc shared between all queues. The following patches will introduce a classful dummy qdisc, which will be used as root qdisc and contain the per-queue qdiscs as children. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-04 14:41:18 +08:00
dev->qdisc = &noop_qdisc;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
net: dynamic ingress_queue allocation ingress being not used very much, and net_device->ingress_queue being quite a big object (128 or 256 bytes), use a dynamic allocation if needed (tc qdisc add dev eth0 ingress ...) dev_ingress_queue(dev) helper should be used only with RTNL taken. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-02 14:11:55 +08:00
if (dev_ingress_queue(dev))
dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net: sched: Convert timers to use timer_setup() In preparation for unconditionally passing the struct timer_list pointer to all timer callbacks, switch to using the new timer_setup() and from_timer() to pass the timer pointer explicitly. Add pointer back to Qdisc. Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook <keescook@chromium.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-17 08:29:17 +08:00
timer_setup(&dev->watchdog_timer, dev_watchdog, 0);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
static void shutdown_scheduler_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc_default)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
struct Qdisc *qdisc_default = _qdisc_default;
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
if (qdisc) {
pkt_sched: Use rcu_assign_pointer() to change dev_queue->qdisc These pointers are RCU protected, so proper primitives should be used. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-27 17:22:07 +08:00
rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
dev_queue->qdisc_sleeping = qdisc_default;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
net: sched: rename qdisc_destroy() to qdisc_put() Current implementation of qdisc_destroy() decrements Qdisc reference counter and only actually destroy Qdisc if reference counter value reached zero. Rename qdisc_destroy() to qdisc_put() in order for it to better describe the way in which this function currently implemented and used. Extract code that deallocates Qdisc into new private qdisc_destroy() function. It is intended to be shared between regular qdisc_put() and its unlocked version that is introduced in next patch in this series. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:50 +08:00
qdisc_put(qdisc);
[NET] SCHED: Fix whitespace errors. Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-02-09 22:25:16 +08:00
}
netdev: Move rest of qdisc state into struct netdev_queue Now qdisc, qdisc_sleeping, and qdisc_list also live there. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-09 08:42:10 +08:00
}
void dev_shutdown(struct net_device *dev)
{
netdev: Allocate multiple queues for TX. alloc_netdev_mq() now allocates an array of netdev_queue structures for TX, based upon the queue_count argument. Furthermore, all accesses to the TX queues are now vectored through the netdev_get_tx_queue() and netdev_for_each_tx_queue() interfaces. This makes it easy to grep the tree for all things that want to get to a TX queue of a net device. Problem spots which are not really multiqueue aware yet, and only work with one queue, can easily be spotted by grepping for all netdev_get_tx_queue() calls that pass in a zero index. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-17 15:34:19 +08:00
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
net: dynamic ingress_queue allocation ingress being not used very much, and net_device->ingress_queue being quite a big object (128 or 256 bytes), use a dynamic allocation if needed (tc qdisc add dev eth0 ingress ...) dev_ingress_queue(dev) helper should be used only with RTNL taken. Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-02 14:11:55 +08:00
if (dev_ingress_queue(dev))
shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
net: sched: rename qdisc_destroy() to qdisc_put() Current implementation of qdisc_destroy() decrements Qdisc reference counter and only actually destroy Qdisc if reference counter value reached zero. Rename qdisc_destroy() to qdisc_put() in order for it to better describe the way in which this function currently implemented and used. Extract code that deallocates Qdisc into new private qdisc_destroy() function. It is intended to be shared between regular qdisc_put() and its unlocked version that is introduced in next patch in this series. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-09-25 00:22:50 +08:00
qdisc_put(dev->qdisc);
net_sched: reintroduce dev->qdisc for use by sch_api Currently the multiqueue integration with the qdisc API suffers from a few problems: - with multiple queues, all root qdiscs use the same handle. This means they can't be exposed to userspace in a backwards compatible fashion. - all API operations always refer to queue number 0. Newly created qdiscs are automatically shared between all queues, its not possible to address individual queues or restore multiqueue behaviour once a shared qdisc has been attached. - Dumps only contain the root qdisc of queue 0, in case of non-shared qdiscs this means the statistics are incomplete. This patch reintroduces dev->qdisc, which points to the (single) root qdisc from userspace's point of view. Currently it either points to the first (non-shared) default qdisc, or a qdisc shared between all queues. The following patches will introduce a classful dummy qdisc, which will be used as root qdisc and contain the per-queue qdiscs as children. Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-09-04 14:41:18 +08:00
dev->qdisc = &noop_qdisc;
net: convert BUG_TRAP to generic WARN_ON Removes legacy reinvent-the-wheel type thing. The generic machinery integrates much better to automated debugging aids such as kerneloops.org (and others), and is unambiguous due to better naming. Non-intuively BUG_TRAP() is actually equal to WARN_ON() rather than BUG_ON() though some might actually be promoted to BUG_ON() but I left that to future. I could make at least one BUILD_BUG_ON conversion. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-07-26 12:43:18 +08:00
WARN_ON(timer_pending(&dev->watchdog_timer));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
sch: make htb_rate_cfg and functions around that generic As it is going to be used in tbf as well, push these to generic code. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 08:12:03 +08:00
net_sched: restore "overhead xxx" handling commit 56b765b79 ("htb: improved accuracy at high rates") broke the "overhead xxx" handling, as well as the "linklayer atm" attribute. tc class add ... htb rate X ceil Y linklayer atm overhead 10 This patch restores the "overhead xxx" handling, for htb, tbf and act_police The "linklayer atm" thing needs a separate fix. Reported-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vimalkumar <j.vimal@gmail.com> Cc: Jiri Pirko <jpirko@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-02 21:55:05 +08:00
void psched_ratecfg_precompute(struct psched_ratecfg *r,
net_sched: add u64 rate to psched_ratecfg_precompute() Add an extra u64 rate parameter to psched_ratecfg_precompute() so that some qdisc can opt-in for 64bit rates in the future, to overcome the ~34 Gbits limit. psched_ratecfg_getrate() reports a legacy structure to tc utility, so if actual rate is above the 32bit rate field, cap it to the 34Gbit limit. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-20 00:10:03 +08:00
const struct tc_ratespec *conf,
u64 rate64)
sch: make htb_rate_cfg and functions around that generic As it is going to be used in tbf as well, push these to generic code. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 08:12:03 +08:00
{
net_sched: restore "overhead xxx" handling commit 56b765b79 ("htb: improved accuracy at high rates") broke the "overhead xxx" handling, as well as the "linklayer atm" attribute. tc class add ... htb rate X ceil Y linklayer atm overhead 10 This patch restores the "overhead xxx" handling, for htb, tbf and act_police The "linklayer atm" thing needs a separate fix. Reported-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Vimalkumar <j.vimal@gmail.com> Cc: Jiri Pirko <jpirko@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-02 21:55:05 +08:00
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
net_sched: add u64 rate to psched_ratecfg_precompute() Add an extra u64 rate parameter to psched_ratecfg_precompute() so that some qdisc can opt-in for 64bit rates in the future, to overcome the ~34 Gbits limit. psched_ratecfg_getrate() reports a legacy structure to tc utility, so if actual rate is above the 32bit rate field, cap it to the 34Gbit limit. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-20 00:10:03 +08:00
r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
net_sched: restore "linklayer atm" handling commit 56b765b79 ("htb: improved accuracy at high rates") broke the "linklayer atm" handling. tc class add ... htb rate X ceil Y linklayer atm The linklayer setting is implemented by modifying the rate table which is send to the kernel. No direct parameter were transferred to the kernel indicating the linklayer setting. The commit 56b765b79 ("htb: improved accuracy at high rates") removed the use of the rate table system. To keep compatible with older iproute2 utils, this patch detects the linklayer by parsing the rate table. It also supports future versions of iproute2 to send this linklayer parameter to the kernel directly. This is done by using the __reserved field in struct tc_ratespec, to convey the choosen linklayer option, but only using the lower 4 bits of this field. Linklayer detection is limited to speeds below 100Mbit/s, because at high rates the rtab is gets too inaccurate, so bad that several fields contain the same values, this resembling the ATM detect. Fields even start to contain "0" time to send, e.g. at 1000Mbit/s sending a 96 bytes packet cost "0", thus the rtab have been more broken than we first realized. Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-08-15 05:47:11 +08:00
r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
sch: make htb_rate_cfg and functions around that generic As it is going to be used in tbf as well, push these to generic code. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 08:12:03 +08:00
r->mult = 1;
/*
net_sched: psched_ratecfg_precompute() improvements Before allowing 64bits bytes rates, refactor psched_ratecfg_precompute() to get better comments and increased accuracy. rate_bps field is renamed to rate_bytes_ps, as we only have to worry about bytes per second. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Greear <greearb@candelatech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-07 04:56:19 +08:00
* 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.
sch: make htb_rate_cfg and functions around that generic As it is going to be used in tbf as well, push these to generic code. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 08:12:03 +08:00
*/
net_sched: psched_ratecfg_precompute() improvements Before allowing 64bits bytes rates, refactor psched_ratecfg_precompute() to get better comments and increased accuracy. rate_bps field is renamed to rate_bytes_ps, as we only have to worry about bytes per second. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Greear <greearb@candelatech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-07 04:56:19 +08:00
if (r->rate_bytes_ps > 0) {
u64 factor = NSEC_PER_SEC;
for (;;) {
r->mult = div64_u64(factor, r->rate_bytes_ps);
if (r->mult & (1U << 31) || factor & (1ULL << 63))
sch: make htb_rate_cfg and functions around that generic As it is going to be used in tbf as well, push these to generic code. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 08:12:03 +08:00
break;
net_sched: psched_ratecfg_precompute() improvements Before allowing 64bits bytes rates, refactor psched_ratecfg_precompute() to get better comments and increased accuracy. rate_bps field is renamed to rate_bytes_ps, as we only have to worry about bytes per second. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Greear <greearb@candelatech.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-06-07 04:56:19 +08:00
factor <<= 1;
r->shift++;
sch: make htb_rate_cfg and functions around that generic As it is going to be used in tbf as well, push these to generic code. Signed-off-by: Jiri Pirko <jiri@resnulli.us> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-02-12 08:12:03 +08:00
}
}
}
EXPORT_SYMBOL(psched_ratecfg_precompute);
net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-03 18:46:25 +08:00
static void mini_qdisc_rcu_func(struct rcu_head *head)
{
}
void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
struct tcf_proto *tp_head)
{
net: sched: protect filter_chain list with filter_chain_lock mutex Extend tcf_chain with new filter_chain_lock mutex. Always lock the chain when accessing filter_chain list, instead of relying on rtnl lock. Dereference filter_chain with tcf_chain_dereference() lockdep macro to verify that all users of chain_list have the lock taken. Rearrange tp insert/remove code in tc_new_tfilter/tc_del_tfilter to execute all necessary code while holding chain lock in order to prevent invalidation of chain_info structure by potential concurrent change. This also serializes calls to tcf_chain0_head_change(), which allows head change callbacks to rely on filter_chain_lock for synchronization instead of rtnl mutex. Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-02-11 16:55:38 +08:00
/* 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);
net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-03 18:46:25 +08:00
struct mini_Qdisc *miniq;
if (!tp_head) {
RCU_INIT_POINTER(*miniqp->p_miniq, NULL);
net_sched: fix a missing rcu barrier in mini_qdisc_pair_swap() The rcu_barrier_bh() in mini_qdisc_pair_swap() is to wait for flying RCU callback installed by a previous mini_qdisc_pair_swap(), however we miss it on the tp_head==NULL path, which leads to that the RCU callback still uses miniq_old->rcu after it is freed together with qdisc in qdisc_graft(). So just add it on that path too. Fixes: 46209401f8f6 ("net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath ") Reported-by: Jakub Kicinski <jakub.kicinski@netronome.com> Tested-by: Jakub Kicinski <jakub.kicinski@netronome.com> Cc: Jiri Pirko <jiri@mellanox.com> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 15:26:24 +08:00
/* Wait for flying RCU callback before it is freed. */
net/sched: Replace call_rcu_bh() and rcu_barrier_bh() Now that call_rcu()'s callback is not invoked until after bh-disable regions of code have completed (in addition to explicitly marked RCU read-side critical sections), call_rcu() can be used in place of call_rcu_bh(). Similarly, rcu_barrier() can be used in place o frcu_barrier_bh(). This commit therefore makes these changes. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: <netdev@vger.kernel.org>
2018-11-07 11:40:39 +08:00
rcu_barrier();
net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-03 18:46:25 +08:00
return;
}
miniq = !miniq_old || miniq_old == &miniqp->miniq2 ?
&miniqp->miniq1 : &miniqp->miniq2;
/* We need to make sure that readers won't see the miniq
net/sched: Replace call_rcu_bh() and rcu_barrier_bh() Now that call_rcu()'s callback is not invoked until after bh-disable regions of code have completed (in addition to explicitly marked RCU read-side critical sections), call_rcu() can be used in place of call_rcu_bh(). Similarly, rcu_barrier() can be used in place o frcu_barrier_bh(). This commit therefore makes these changes. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: <netdev@vger.kernel.org>
2018-11-07 11:40:39 +08:00
* we are about to modify. So wait until previous call_rcu callback
net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-03 18:46:25 +08:00
* is done.
*/
net/sched: Replace call_rcu_bh() and rcu_barrier_bh() Now that call_rcu()'s callback is not invoked until after bh-disable regions of code have completed (in addition to explicitly marked RCU read-side critical sections), call_rcu() can be used in place of call_rcu_bh(). Similarly, rcu_barrier() can be used in place o frcu_barrier_bh(). This commit therefore makes these changes. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: <netdev@vger.kernel.org>
2018-11-07 11:40:39 +08:00
rcu_barrier();
net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-03 18:46:25 +08:00
miniq->filter_list = tp_head;
rcu_assign_pointer(*miniqp->p_miniq, miniq);
if (miniq_old)
net_sched: fix a missing rcu barrier in mini_qdisc_pair_swap() The rcu_barrier_bh() in mini_qdisc_pair_swap() is to wait for flying RCU callback installed by a previous mini_qdisc_pair_swap(), however we miss it on the tp_head==NULL path, which leads to that the RCU callback still uses miniq_old->rcu after it is freed together with qdisc in qdisc_graft(). So just add it on that path too. Fixes: 46209401f8f6 ("net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath ") Reported-by: Jakub Kicinski <jakub.kicinski@netronome.com> Tested-by: Jakub Kicinski <jakub.kicinski@netronome.com> Cc: Jiri Pirko <jiri@mellanox.com> Cc: John Fastabend <john.fastabend@gmail.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Acked-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-12-21 15:26:24 +08:00
/* This is counterpart of the rcu barriers above. We need to
net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-03 18:46:25 +08:00
* block potential new user of miniq_old until all readers
* are not seeing it.
*/
net/sched: Replace call_rcu_bh() and rcu_barrier_bh() Now that call_rcu()'s callback is not invoked until after bh-disable regions of code have completed (in addition to explicitly marked RCU read-side critical sections), call_rcu() can be used in place of call_rcu_bh(). Similarly, rcu_barrier() can be used in place o frcu_barrier_bh(). This commit therefore makes these changes. Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Jiri Pirko <jiri@resnulli.us> Cc: "David S. Miller" <davem@davemloft.net> Cc: <netdev@vger.kernel.org>
2018-11-07 11:40:39 +08:00
call_rcu(&miniq_old->rcu, mini_qdisc_rcu_func);
net: core: introduce mini_Qdisc and eliminate usage of tp->q for clsact fastpath In sch_handle_egress and sch_handle_ingress tp->q is used only in order to update stats. So stats and filter list are the only things that are needed in clsact qdisc fastpath processing. Introduce new mini_Qdisc struct to hold those items. Also, introduce a helper to swap the mini_Qdisc structures in case filter list head changes. This removes need for tp->q usage without added overhead. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-11-03 18:46:25 +08:00
}
EXPORT_SYMBOL(mini_qdisc_pair_swap);
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->p_miniq = p_miniq;
}
EXPORT_SYMBOL(mini_qdisc_pair_init);