linux/net/sched/sch_generic.c

947 lines
23 KiB
C
Raw Normal View History

/*
* 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 09:04:11 +01:00
#include <linux/slab.h>
#include <linux/if_vlan.h>
#include <net/sch_generic.h>
#include <net/pkt_sched.h>
#include <net/dst.h>
/* Qdisc to use by default */
const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops;
EXPORT_SYMBOL(default_qdisc_ops);
/* Main transmission queue. */
/* Modifications to data participating in scheduling must be protected with
* qdisc_lock(qdisc) spinlock.
*
* The idea is the following:
* - enqueue, dequeue are serialized via qdisc root lock
* - ingress filtering is also serialized via qdisc root lock
* - updates to tree and tree walking are only done under the rtnl mutex.
*/
static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
{
skb_dst_force(skb);
q->gso_skb = skb;
q->qstats.requeues++;
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 03:44:21 +02:00
q->q.qlen++; /* it's still part of the queue */
__netif_schedule(q);
return 0;
}
static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
{
struct sk_buff *skb = q->gso_skb;
const struct netdev_queue *txq = q->dev_queue;
if (unlikely(skb)) {
/* check the reason of requeuing without tx lock first */
txq = netdev_get_tx_queue(txq->dev, skb_get_queue_mapping(skb));
if (!netif_xmit_frozen_or_stopped(txq)) {
q->gso_skb = 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 03:44:21 +02:00
q->q.qlen--;
} else
skb = NULL;
} else {
if (!(q->flags & TCQ_F_ONETXQUEUE) || !netif_xmit_frozen_or_stopped(txq))
skb = q->dequeue(q);
}
return skb;
}
[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 04:56:09 +02:00
static inline int handle_dev_cpu_collision(struct sk_buff *skb,
struct netdev_queue *dev_queue,
[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 04:56:09 +02:00
struct Qdisc *q)
{
[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 04:56:09 +02:00
int ret;
if (unlikely(dev_queue->xmit_lock_owner == smp_processor_id())) {
[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 04:56:09 +02:00
/*
* Same CPU holding the lock. It may be a transient
* configuration error, when hard_start_xmit() recurses. We
* detect it by checking xmit owner and drop the packet when
* deadloop is detected. Return OK to try the next skb.
*/
kfree_skb(skb);
net_warn_ratelimited("Dead loop on netdevice %s, fix it urgently!\n",
dev_queue->dev->name);
[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 04:56:09 +02:00
ret = qdisc_qlen(q);
} else {
/*
* Another cpu is holding lock, requeue & delay xmits for
* some time.
*/
__this_cpu_inc(softnet_data.cpu_collision);
ret = dev_requeue_skb(skb, q);
}
[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 04:56:09 +02:00
return ret;
}
/*
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 03:44:21 +02:00
* Transmit one skb, and handle the return status as required. Holding the
* __QDISC_STATE_RUNNING bit guarantees that only one CPU can execute this
* function.
[NET]: qdisc_restart - readability changes plus one bug fix. New changes : - Incorporated Peter Waskiewicz's comments. - Re-added back one warning message (on driver returning wrong value). Previous changes : - Converted to use switch/case code which looks neater. - "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless check should be removed, since driver will return NETDEV_TX_LOCKED only if lockless is true and driver has to do the locking. In the original code as well as the latest code, this code can result in a bug where if LLTX is not set for a driver (lockless == 0) but the driver is written wrongly to do a trylock (despite LLTX being set), the driver returns LOCKED. But since lockless is zero, the packet is requeue'd instead of calling collision code which will issue warning and free up the skb. Instead this skb will be retried with this driver next time, and the same result will ensue. Removing this check will catch these driver bugs instead of hiding the problem. I am keeping this change to readability section since : a. it is confusing to check two things as it is; and b. it is difficult to keep this check in the changed 'switch' code. - Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is the work being done and easier to understand) and do_dev_requeue to dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to dev_handle_collision (handle_dev_cpu_collision is a small routine with only one caller, so there is no need to have two separate routines which also results in getting rid of two macros, etc. - Removed an XXX comment as it should never fail (I suspect this was related to batch skb WIP, Jamal ?). Converted some functions to original coding style of having the return values and the function name on same line, eg prio2list. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-25 04:56:09 +02:00
*
* Returns to the caller:
* 0 - queue is empty or throttled.
* >0 - queue is not empty.
*/
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 03:44:21 +02:00
int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
struct net_device *dev, struct netdev_queue *txq,
spinlock_t *root_lock)
{
int ret = NETDEV_TX_BUSY;
/* And release qdisc */
spin_unlock(root_lock);
HARD_TX_LOCK(dev, txq, smp_processor_id());
if (!netif_xmit_frozen_or_stopped(txq))
net: core: explicitly select a txq before doing l2 forwarding Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The will cause several issues: - NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan instead of lower device which misses the necessary txq synchronization for lower device such as txq stopping or frozen required by dev watchdog or control path. - dev_hard_start_xmit() was called with NULL txq which bypasses the net device watchdog. - dev_hard_start_xmit() does not check txq everywhere which will lead a crash when tso is disabled for lower device. Fix this by explicitly introducing a new param for .ndo_select_queue() for just selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also extended to accept this parameter and dev_queue_xmit_accel() was used to do l2 forwarding transmission. With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of dev_queue_xmit() to do the transmission. In the future, it was also required for macvtap l2 forwarding support since it provides a necessary synchronization method. Cc: John Fastabend <john.r.fastabend@intel.com> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: e1000-devel@lists.sourceforge.net Signed-off-by: Jason Wang <jasowang@redhat.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-10 09:18:26 +01:00
ret = dev_hard_start_xmit(skb, dev, txq);
HARD_TX_UNLOCK(dev, txq);
spin_lock(root_lock);
if (dev_xmit_complete(ret)) {
/* Driver sent out skb successfully or skb was consumed */
[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 04:56:09 +02:00
ret = qdisc_qlen(q);
} else if (ret == NETDEV_TX_LOCKED) {
[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 04:56:09 +02:00
/* Driver try lock failed */
ret = handle_dev_cpu_collision(skb, txq, q);
} else {
[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 04:56:09 +02:00
/* Driver returned NETDEV_TX_BUSY - requeue skb */
if (unlikely(ret != NETDEV_TX_BUSY))
net_warn_ratelimited("BUG %s code %d qlen %d\n",
dev->name, ret, q->q.qlen);
[NET]: qdisc_restart - readability changes plus one bug fix. New changes : - Incorporated Peter Waskiewicz's comments. - Re-added back one warning message (on driver returning wrong value). Previous changes : - Converted to use switch/case code which looks neater. - "if (ret == NETDEV_TX_LOCKED && lockless)" is buggy, and the lockless check should be removed, since driver will return NETDEV_TX_LOCKED only if lockless is true and driver has to do the locking. In the original code as well as the latest code, this code can result in a bug where if LLTX is not set for a driver (lockless == 0) but the driver is written wrongly to do a trylock (despite LLTX being set), the driver returns LOCKED. But since lockless is zero, the packet is requeue'd instead of calling collision code which will issue warning and free up the skb. Instead this skb will be retried with this driver next time, and the same result will ensue. Removing this check will catch these driver bugs instead of hiding the problem. I am keeping this change to readability section since : a. it is confusing to check two things as it is; and b. it is difficult to keep this check in the changed 'switch' code. - Changed some names, like try_get_tx_pkt to dev_dequeue_skb (as that is the work being done and easier to understand) and do_dev_requeue to dev_requeue_skb, merged handle_dev_cpu_collision and tx_islocked to dev_handle_collision (handle_dev_cpu_collision is a small routine with only one caller, so there is no need to have two separate routines which also results in getting rid of two macros, etc. - Removed an XXX comment as it should never fail (I suspect this was related to batch skb WIP, Jamal ?). Converted some functions to original coding style of having the return values and the function name on same line, eg prio2list. Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-06-25 04:56:09 +02:00
ret = dev_requeue_skb(skb, q);
[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 04:56:09 +02:00
}
if (ret && netif_xmit_frozen_or_stopped(txq))
ret = 0;
[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 04:56:09 +02:00
return ret;
}
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 03:44:21 +02:00
/*
* NOTE: Called under qdisc_lock(q) with locally disabled BH.
*
* __QDISC_STATE_RUNNING guarantees only one CPU can process
* this qdisc at a time. qdisc_lock(q) serializes queue accesses for
* this queue.
*
* netif_tx_lock serializes accesses to device driver.
*
* qdisc_lock(q) and netif_tx_lock are mutually exclusive,
* if one is grabbed, another must be free.
*
* Note, that this procedure can be called by a watchdog timer
*
* Returns to the caller:
* 0 - queue is empty or throttled.
* >0 - queue is not empty.
*
*/
static inline int qdisc_restart(struct Qdisc *q)
{
struct netdev_queue *txq;
struct net_device *dev;
spinlock_t *root_lock;
struct sk_buff *skb;
/* Dequeue packet */
skb = dequeue_skb(q);
if (unlikely(!skb))
return 0;
WARN_ON_ONCE(skb_dst_is_noref(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 03:44:21 +02:00
root_lock = qdisc_lock(q);
dev = qdisc_dev(q);
txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
return sch_direct_xmit(skb, q, dev, txq, root_lock);
}
void __qdisc_run(struct Qdisc *q)
{
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 10:13:54 +02:00
int quota = weight_p;
while (qdisc_restart(q)) {
/*
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 10:13:54 +02:00
* Ordered by possible occurrence: Postpone processing if
* 1. we've exceeded packet quota
* 2. another process needs the CPU;
*/
if (--quota <= 0 || need_resched()) {
__netif_schedule(q);
break;
}
}
qdisc_run_end(q);
}
unsigned long dev_trans_start(struct net_device *dev)
{
unsigned long val, res;
unsigned int i;
if (is_vlan_dev(dev))
dev = vlan_dev_real_dev(dev);
res = dev->trans_start;
for (i = 0; i < dev->num_tx_queues; i++) {
val = netdev_get_tx_queue(dev, i)->trans_start;
if (val && time_after(val, res))
res = val;
}
dev->trans_start = res;
return res;
}
EXPORT_SYMBOL(dev_trans_start);
static void dev_watchdog(unsigned long arg)
{
struct net_device *dev = (struct net_device *)arg;
[NET]: Add netif_tx_lock Various drivers use xmit_lock internally to synchronise with their transmission routines. They do so without setting xmit_lock_owner. This is fine as long as netpoll is not in use. With netpoll it is possible for deadlocks to occur if xmit_lock_owner isn't set. This is because if a printk occurs while xmit_lock is held and xmit_lock_owner is not set can cause netpoll to attempt to take xmit_lock recursively. While it is possible to resolve this by getting netpoll to use trylock, it is suboptimal because netpoll's sole objective is to maximise the chance of getting the printk out on the wire. So delaying or dropping the message is to be avoided as much as possible. So the only alternative is to always set xmit_lock_owner. The following patch does this by introducing the netif_tx_lock family of functions that take care of setting/unsetting xmit_lock_owner. I renamed xmit_lock to _xmit_lock to indicate that it should not be used directly. I didn't provide irq versions of the netif_tx_lock functions since xmit_lock is meant to be a BH-disabling lock. This is pretty much a straight text substitution except for a small bug fix in winbond. It currently uses netif_stop_queue/spin_unlock_wait to stop transmission. This is unsafe as an IRQ can potentially wake up the queue. So it is safer to use netif_tx_disable. The hamradio bits used spin_lock_irq but it is unnecessary as xmit_lock must never be taken in an IRQ handler. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-09 21:20:56 +02:00
netif_tx_lock(dev);
if (!qdisc_tx_is_noop(dev)) {
if (netif_device_present(dev) &&
netif_running(dev) &&
netif_carrier_ok(dev)) {
int some_queue_timedout = 0;
unsigned int i;
unsigned long trans_start;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *txq;
txq = netdev_get_tx_queue(dev, i);
/*
* old device drivers set dev->trans_start
*/
trans_start = txq->trans_start ? : dev->trans_start;
if (netif_xmit_stopped(txq) &&
time_after(jiffies, (trans_start +
dev->watchdog_timeo))) {
some_queue_timedout = 1;
txq->trans_timeout++;
break;
}
}
if (some_queue_timedout) {
WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n",
dev->name, netdev_drivername(dev), i);
dev->netdev_ops->ndo_tx_timeout(dev);
}
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies +
dev->watchdog_timeo)))
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>
2006-06-09 21:20:56 +02:00
netif_tx_unlock(dev);
dev_put(dev);
}
void __netdev_watchdog_up(struct net_device *dev)
{
if (dev->netdev_ops->ndo_tx_timeout) {
if (dev->watchdog_timeo <= 0)
dev->watchdog_timeo = 5*HZ;
if (!mod_timer(&dev->watchdog_timer,
round_jiffies(jiffies + dev->watchdog_timeo)))
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>
2006-06-09 21:20:56 +02:00
netif_tx_lock_bh(dev);
if (del_timer(&dev->watchdog_timer))
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>
2006-06-09 21:20:56 +02:00
netif_tx_unlock_bh(dev);
}
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 01:41:36 +02:00
/**
* netif_carrier_on - set carrier
* @dev: network device
*
* Device has detected that carrier.
*/
void netif_carrier_on(struct net_device *dev)
{
if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
linkwatch_fire_event(dev);
if (netif_running(dev))
__netdev_watchdog_up(dev);
}
}
EXPORT_SYMBOL(netif_carrier_on);
[NET]: Make NAPI polling independent of struct net_device objects. Several devices have multiple independant RX queues per net device, and some have a single interrupt doorbell for several queues. In either case, it's easier to support layouts like that if the structure representing the poll is independant from the net device itself. The signature of the ->poll() call back goes from: int foo_poll(struct net_device *dev, int *budget) to int foo_poll(struct napi_struct *napi, int budget) The caller is returned the number of RX packets processed (or the number of "NAPI credits" consumed if you want to get abstract). The callee no longer messes around bumping dev->quota, *budget, etc. because that is all handled in the caller upon return. The napi_struct is to be embedded in the device driver private data structures. Furthermore, it is the driver's responsibility to disable all NAPI instances in it's ->stop() device close handler. Since the napi_struct is privatized into the driver's private data structures, only the driver knows how to get at all of the napi_struct instances it may have per-device. With lots of help and suggestions from Rusty Russell, Roland Dreier, Michael Chan, Jeff Garzik, and Jamal Hadi Salim. Bug fixes from Thomas Graf, Roland Dreier, Peter Zijlstra, Joseph Fannin, Scott Wood, Hans J. Koch, and Michael Chan. [ Ported to current tree and all drivers converted. Integrated Stephen's follow-on kerneldoc additions, and restored poll_list handling to the old style to fix mutual exclusion issues. -DaveM ] Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-04 01:41:36 +02:00
/**
* netif_carrier_off - clear carrier
* @dev: network device
*
* Device has detected loss of carrier.
*/
void netif_carrier_off(struct net_device *dev)
{
if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) {
if (dev->reg_state == NETREG_UNINITIALIZED)
return;
linkwatch_fire_event(dev);
}
}
EXPORT_SYMBOL(netif_carrier_off);
/* "NOOP" scheduler: the best scheduler, recommended for all interfaces
under all circumstances. It is difficult to invent anything faster or
cheaper.
*/
static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
{
kfree_skb(skb);
return NET_XMIT_CN;
}
static struct sk_buff *noop_dequeue(struct Qdisc *qdisc)
{
return NULL;
}
struct Qdisc_ops noop_qdisc_ops __read_mostly = {
.id = "noop",
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.peek = noop_dequeue,
.owner = THIS_MODULE,
};
static struct netdev_queue noop_netdev_queue = {
.qdisc = &noop_qdisc,
.qdisc_sleeping = &noop_qdisc,
};
struct Qdisc noop_qdisc = {
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.flags = TCQ_F_BUILTIN,
.ops = &noop_qdisc_ops,
.list = LIST_HEAD_INIT(noop_qdisc.list),
.q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock),
.dev_queue = &noop_netdev_queue,
.busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock),
};
EXPORT_SYMBOL(noop_qdisc);
static struct Qdisc_ops noqueue_qdisc_ops __read_mostly = {
.id = "noqueue",
.priv_size = 0,
.enqueue = noop_enqueue,
.dequeue = noop_dequeue,
.peek = noop_dequeue,
.owner = THIS_MODULE,
};
static struct Qdisc noqueue_qdisc;
static struct netdev_queue noqueue_netdev_queue = {
.qdisc = &noqueue_qdisc,
.qdisc_sleeping = &noqueue_qdisc,
};
static struct Qdisc noqueue_qdisc = {
.enqueue = NULL,
.dequeue = noop_dequeue,
.flags = TCQ_F_BUILTIN,
.ops = &noqueue_qdisc_ops,
.list = LIST_HEAD_INIT(noqueue_qdisc.list),
.q.lock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.q.lock),
.dev_queue = &noqueue_netdev_queue,
.busylock = __SPIN_LOCK_UNLOCKED(noqueue_qdisc.busylock),
};
static const u8 prio2band[TC_PRIO_MAX + 1] = {
1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1
};
/* 3-band FIFO queue: old style, but should be a bit faster than
generic prio+fifo combination.
*/
#define PFIFO_FAST_BANDS 3
/*
* Private data for a pfifo_fast scheduler containing:
* - queues for the three band
* - bitmap indicating which of the bands contain skbs
*/
struct pfifo_fast_priv {
u32 bitmap;
struct sk_buff_head q[PFIFO_FAST_BANDS];
};
/*
* Convert a bitmap to the first band number where an skb is queued, where:
* bitmap=0 means there are no skbs on any band.
* bitmap=1 means there is an skb on band 0.
* bitmap=7 means there are skbs on all 3 bands, etc.
*/
static const int bitmap2band[] = {-1, 0, 1, 0, 2, 0, 1, 0};
static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv,
int band)
{
return priv->q + band;
}
static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc)
{
if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) {
int band = prio2band[skb->priority & TC_PRIO_MAX];
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
struct sk_buff_head *list = band2list(priv, band);
priv->bitmap |= (1 << band);
qdisc->q.qlen++;
return __qdisc_enqueue_tail(skb, qdisc, list);
}
return qdisc_drop(skb, qdisc);
}
static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
{
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
int band = bitmap2band[priv->bitmap];
if (likely(band >= 0)) {
struct sk_buff_head *list = band2list(priv, band);
struct sk_buff *skb = __qdisc_dequeue_head(qdisc, list);
qdisc->q.qlen--;
if (skb_queue_empty(list))
priv->bitmap &= ~(1 << band);
return skb;
}
return NULL;
}
static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc)
{
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
int band = bitmap2band[priv->bitmap];
if (band >= 0) {
struct sk_buff_head *list = band2list(priv, band);
return skb_peek(list);
}
return NULL;
}
static void pfifo_fast_reset(struct Qdisc *qdisc)
{
int prio;
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
__qdisc_reset_queue(qdisc, band2list(priv, prio));
priv->bitmap = 0;
qdisc->qstats.backlog = 0;
qdisc->q.qlen = 0;
}
static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb)
{
struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS };
memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1);
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
return skb->len;
nla_put_failure:
return -1;
}
static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt)
{
int prio;
struct pfifo_fast_priv *priv = qdisc_priv(qdisc);
for (prio = 0; prio < PFIFO_FAST_BANDS; prio++)
skb_queue_head_init(band2list(priv, prio));
/* Can by-pass the queue discipline */
qdisc->flags |= TCQ_F_CAN_BYPASS;
return 0;
}
struct Qdisc_ops pfifo_fast_ops __read_mostly = {
.id = "pfifo_fast",
.priv_size = sizeof(struct pfifo_fast_priv),
.enqueue = pfifo_fast_enqueue,
.dequeue = pfifo_fast_dequeue,
.peek = pfifo_fast_peek,
.init = pfifo_fast_init,
.reset = pfifo_fast_reset,
.dump = pfifo_fast_dump,
.owner = THIS_MODULE,
};
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 03:02:56 +02:00
static struct lock_class_key qdisc_tx_busylock;
struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
const struct Qdisc_ops *ops)
{
void *p;
struct Qdisc *sch;
unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
int err = -ENOBUFS;
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 03:02:56 +02:00
struct net_device *dev = dev_queue->dev;
p = kzalloc_node(size, GFP_KERNEL,
netdev_queue_numa_node_read(dev_queue));
if (!p)
goto errout;
sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
/* 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;
}
INIT_LIST_HEAD(&sch->list);
skb_queue_head_init(&sch->q);
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 03:02:56 +02:00
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 03:02:56 +02:00
lockdep_set_class(&sch->busylock,
dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
sch->ops = ops;
sch->enqueue = ops->enqueue;
sch->dequeue = ops->dequeue;
sch->dev_queue = dev_queue;
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 03:02:56 +02:00
dev_hold(dev);
atomic_set(&sch->refcnt, 1);
return sch;
errout:
return ERR_PTR(err);
}
struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue,
const struct Qdisc_ops *ops,
unsigned int parentid)
{
struct Qdisc *sch;
if (!try_module_get(ops->owner))
goto errout;
sch = qdisc_alloc(dev_queue, ops);
if (IS_ERR(sch))
goto errout;
sch->parent = parentid;
if (!ops->init || ops->init(sch, NULL) == 0)
return sch;
qdisc_destroy(sch);
errout:
return NULL;
}
EXPORT_SYMBOL(qdisc_create_dflt);
/* Under qdisc_lock(qdisc) and BH! */
void qdisc_reset(struct Qdisc *qdisc)
{
const struct Qdisc_ops *ops = qdisc->ops;
if (ops->reset)
ops->reset(qdisc);
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 03:44:21 +02:00
if (qdisc->gso_skb) {
kfree_skb(qdisc->gso_skb);
qdisc->gso_skb = NULL;
qdisc->q.qlen = 0;
}
}
EXPORT_SYMBOL(qdisc_reset);
static void qdisc_rcu_free(struct rcu_head *head)
{
struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
kfree((char *) qdisc - qdisc->padded);
}
void qdisc_destroy(struct Qdisc *qdisc)
{
const struct Qdisc_ops *ops = qdisc->ops;
if (qdisc->flags & TCQ_F_BUILTIN ||
!atomic_dec_and_test(&qdisc->refcnt))
return;
#ifdef CONFIG_NET_SCHED
qdisc_list_del(qdisc);
qdisc_put_stab(rtnl_dereference(qdisc->stab));
#endif
gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est);
if (ops->reset)
ops->reset(qdisc);
if (ops->destroy)
ops->destroy(qdisc);
module_put(ops->owner);
dev_put(qdisc_dev(qdisc));
kfree_skb(qdisc->gso_skb);
/*
* gen_estimator est_timer() might access qdisc->q.lock,
* wait a RCU grace period before freeing qdisc.
*/
call_rcu(&qdisc->rcu_head, qdisc_rcu_free);
}
EXPORT_SYMBOL(qdisc_destroy);
/* 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);
/* Prune old scheduler */
if (oqdisc && atomic_read(&oqdisc->refcnt) <= 1)
qdisc_reset(oqdisc);
/* ... 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 09:06:09 +01:00
EXPORT_SYMBOL(dev_graft_qdisc);
static void attach_one_default_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_unused)
{
struct Qdisc *qdisc = &noqueue_qdisc;
if (dev->tx_queue_len) {
qdisc = qdisc_create_dflt(dev_queue,
default_qdisc_ops, TC_H_ROOT);
if (!qdisc) {
netdev_info(dev, "activation failed\n");
return;
}
if (!netif_is_multiqueue(dev))
qdisc->flags |= TCQ_F_ONETXQUEUE;
}
dev_queue->qdisc_sleeping = qdisc;
}
static void attach_default_qdiscs(struct net_device *dev)
{
struct netdev_queue *txq;
struct Qdisc *qdisc;
txq = netdev_get_tx_queue(dev, 0);
if (!netif_is_multiqueue(dev) || dev->tx_queue_len == 0) {
netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL);
dev->qdisc = txq->qdisc_sleeping;
atomic_inc(&dev->qdisc->refcnt);
} else {
qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT);
if (qdisc) {
dev->qdisc = qdisc;
qdisc->ops->attach(qdisc);
}
}
}
static void transition_one_qdisc(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_need_watchdog)
{
struct Qdisc *new_qdisc = dev_queue->qdisc_sleeping;
int *need_watchdog_p = _need_watchdog;
if (!(new_qdisc->flags & TCQ_F_BUILTIN))
clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state);
rcu_assign_pointer(dev_queue->qdisc, new_qdisc);
if (need_watchdog_p && new_qdisc != &noqueue_qdisc) {
dev_queue->trans_start = 0;
*need_watchdog_p = 1;
}
}
void dev_activate(struct net_device *dev)
{
int need_watchdog;
/* No queueing discipline is attached to device;
* create default one for devices, which need queueing
* and noqueue_qdisc for virtual interfaces
*/
if (dev->qdisc == &noop_qdisc)
attach_default_qdiscs(dev);
if (!netif_carrier_ok(dev))
/* Delay activation until next carrier-on event */
return;
need_watchdog = 0;
netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog);
if (dev_ingress_queue(dev))
transition_one_qdisc(dev, dev_ingress_queue(dev), NULL);
if (need_watchdog) {
dev->trans_start = jiffies;
dev_watchdog_up(dev);
}
}
net_sched: implement a root container qdisc sch_mqprio This implements a mqprio queueing discipline that by default creates a pfifo_fast qdisc per tx queue and provides the needed configuration interface. Using the mqprio qdisc the number of tcs currently in use along with the range of queues alloted to each class can be configured. By default skbs are mapped to traffic classes using the skb priority. This mapping is configurable. Configurable parameters, struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_BITMASK + 1]; __u8 hw; __u16 count[TC_MAX_QUEUE]; __u16 offset[TC_MAX_QUEUE]; }; Here the count/offset pairing give the queue alignment and the prio_tc_map gives the mapping from skb->priority to tc. The hw bit determines if the hardware should configure the count and offset values. If the hardware bit is set then the operation will fail if the hardware does not implement the ndo_setup_tc operation. This is to avoid undetermined states where the hardware may or may not control the queue mapping. Also minimal bounds checking is done on the count/offset to verify a queue does not exceed num_tx_queues and that queue ranges do not overlap. Otherwise it is left to user policy or hardware configuration to create useful mappings. It is expected that hardware QOS schemes can be implemented by creating appropriate mappings of queues in ndo_tc_setup(). One expected use case is drivers will use the ndo_setup_tc to map queue ranges onto 802.1Q traffic classes. This provides a generic mechanism to map network traffic onto these traffic classes and removes the need for lower layer drivers to know specifics about traffic types. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-17 09:06:09 +01:00
EXPORT_SYMBOL(dev_activate);
static void dev_deactivate_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc_default)
{
struct Qdisc *qdisc_default = _qdisc_default;
struct Qdisc *qdisc;
qdisc = dev_queue->qdisc;
if (qdisc) {
spin_lock_bh(qdisc_lock(qdisc));
if (!(qdisc->flags & TCQ_F_BUILTIN))
set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state);
rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
qdisc_reset(qdisc);
spin_unlock_bh(qdisc_lock(qdisc));
}
}
static bool some_qdisc_is_busy(struct net_device *dev)
{
unsigned int i;
for (i = 0; i < dev->num_tx_queues; i++) {
struct netdev_queue *dev_queue;
spinlock_t *root_lock;
struct Qdisc *q;
int val;
dev_queue = netdev_get_tx_queue(dev, i);
q = dev_queue->qdisc_sleeping;
root_lock = qdisc_lock(q);
spin_lock_bh(root_lock);
val = (qdisc_is_running(q) ||
test_bit(__QDISC_STATE_SCHED, &q->state));
spin_unlock_bh(root_lock);
if (val)
return true;
}
return false;
}
/**
* dev_deactivate_many - deactivate transmissions on several devices
* @head: list of devices to deactivate
*
* This function returns only when all outstanding transmissions
* have completed, unless all devices are in dismantle phase.
*/
void dev_deactivate_many(struct list_head *head)
{
struct net_device *dev;
bool sync_needed = false;
list_for_each_entry(dev, head, close_list) {
netdev_for_each_tx_queue(dev, dev_deactivate_queue,
&noop_qdisc);
if (dev_ingress_queue(dev))
dev_deactivate_queue(dev, dev_ingress_queue(dev),
&noop_qdisc);
dev_watchdog_down(dev);
sync_needed |= !dev->dismantle;
}
/* 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
*/
if (sync_needed)
synchronize_net();
/* Wait for outstanding qdisc_run calls. */
list_for_each_entry(dev, head, close_list)
while (some_qdisc_is_busy(dev))
yield();
}
void dev_deactivate(struct net_device *dev)
{
LIST_HEAD(single);
list_add(&dev->close_list, &single);
dev_deactivate_many(&single);
list_del(&single);
}
net_sched: implement a root container qdisc sch_mqprio This implements a mqprio queueing discipline that by default creates a pfifo_fast qdisc per tx queue and provides the needed configuration interface. Using the mqprio qdisc the number of tcs currently in use along with the range of queues alloted to each class can be configured. By default skbs are mapped to traffic classes using the skb priority. This mapping is configurable. Configurable parameters, struct tc_mqprio_qopt { __u8 num_tc; __u8 prio_tc_map[TC_BITMASK + 1]; __u8 hw; __u16 count[TC_MAX_QUEUE]; __u16 offset[TC_MAX_QUEUE]; }; Here the count/offset pairing give the queue alignment and the prio_tc_map gives the mapping from skb->priority to tc. The hw bit determines if the hardware should configure the count and offset values. If the hardware bit is set then the operation will fail if the hardware does not implement the ndo_setup_tc operation. This is to avoid undetermined states where the hardware may or may not control the queue mapping. Also minimal bounds checking is done on the count/offset to verify a queue does not exceed num_tx_queues and that queue ranges do not overlap. Otherwise it is left to user policy or hardware configuration to create useful mappings. It is expected that hardware QOS schemes can be implemented by creating appropriate mappings of queues in ndo_tc_setup(). One expected use case is drivers will use the ndo_setup_tc to map queue ranges onto 802.1Q traffic classes. This provides a generic mechanism to map network traffic onto these traffic classes and removes the need for lower layer drivers to know specifics about traffic types. Signed-off-by: John Fastabend <john.r.fastabend@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-01-17 09:06:09 +01:00
EXPORT_SYMBOL(dev_deactivate);
static void dev_init_scheduler_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc)
{
struct Qdisc *qdisc = _qdisc;
dev_queue->qdisc = qdisc;
dev_queue->qdisc_sleeping = qdisc;
}
void dev_init_scheduler(struct net_device *dev)
{
dev->qdisc = &noop_qdisc;
netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc);
if (dev_ingress_queue(dev))
dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
setup_timer(&dev->watchdog_timer, dev_watchdog, (unsigned long)dev);
}
static void shutdown_scheduler_queue(struct net_device *dev,
struct netdev_queue *dev_queue,
void *_qdisc_default)
{
struct Qdisc *qdisc = dev_queue->qdisc_sleeping;
struct Qdisc *qdisc_default = _qdisc_default;
if (qdisc) {
rcu_assign_pointer(dev_queue->qdisc, qdisc_default);
dev_queue->qdisc_sleeping = qdisc_default;
qdisc_destroy(qdisc);
}
}
void dev_shutdown(struct net_device *dev)
{
netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc);
if (dev_ingress_queue(dev))
shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc);
qdisc_destroy(dev->qdisc);
dev->qdisc = &noop_qdisc;
WARN_ON(timer_pending(&dev->watchdog_timer));
}
void psched_ratecfg_precompute(struct psched_ratecfg *r,
const struct tc_ratespec *conf,
u64 rate64)
{
memset(r, 0, sizeof(*r));
r->overhead = conf->overhead;
r->rate_bytes_ps = max_t(u64, conf->rate, rate64);
r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK);
r->mult = 1;
/*
* 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.
*/
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))
break;
factor <<= 1;
r->shift++;
}
}
}
EXPORT_SYMBOL(psched_ratecfg_precompute);