linux/net/sched/sch_multiq.c

422 lines
8.8 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2008, Intel Corporation.
*
* Author: Alexander Duyck <alexander.h.duyck@intel.com>
*/
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/pkt_cls.h>
struct multiq_sched_data {
u16 bands;
u16 max_bands;
u16 curband;
struct tcf_proto __rcu *filter_list;
struct tcf_block *block;
struct Qdisc **queues;
};
static struct Qdisc *
multiq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr)
{
struct multiq_sched_data *q = qdisc_priv(sch);
u32 band;
struct tcf_result res;
struct tcf_proto *fl = rcu_dereference_bh(q->filter_list);
int err;
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
err = tcf_classify(skb, fl, &res, false);
#ifdef CONFIG_NET_CLS_ACT
switch (err) {
case TC_ACT_STOLEN:
case TC_ACT_QUEUED:
case TC_ACT_TRAP:
*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
fallthrough;
case TC_ACT_SHOT:
return NULL;
}
#endif
band = skb_get_queue_mapping(skb);
if (band >= q->bands)
return q->queues[0];
return q->queues[band];
}
static int
multiq_enqueue(struct sk_buff *skb, struct Qdisc *sch,
struct sk_buff **to_free)
{
struct Qdisc *qdisc;
int ret;
qdisc = multiq_classify(skb, sch, &ret);
#ifdef CONFIG_NET_CLS_ACT
if (qdisc == NULL) {
if (ret & __NET_XMIT_BYPASS)
qdisc_qstats_drop(sch);
__qdisc_drop(skb, to_free);
return ret;
}
#endif
ret = qdisc_enqueue(skb, qdisc, to_free);
if (ret == NET_XMIT_SUCCESS) {
sch->q.qlen++;
return NET_XMIT_SUCCESS;
}
if (net_xmit_drop_count(ret))
qdisc_qstats_drop(sch);
return ret;
}
static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
{
struct multiq_sched_data *q = qdisc_priv(sch);
struct Qdisc *qdisc;
struct sk_buff *skb;
int band;
for (band = 0; band < q->bands; band++) {
/* cycle through bands to ensure fairness */
q->curband++;
if (q->curband >= q->bands)
q->curband = 0;
/* Check that target subqueue is available before
* pulling an skb to avoid head-of-line blocking.
*/
if (!netif_xmit_stopped(
netdev_get_tx_queue(qdisc_dev(sch), q->curband))) {
qdisc = q->queues[q->curband];
skb = qdisc->dequeue(qdisc);
if (skb) {
qdisc_bstats_update(sch, skb);
sch->q.qlen--;
return skb;
}
}
}
return NULL;
}
static struct sk_buff *multiq_peek(struct Qdisc *sch)
{
struct multiq_sched_data *q = qdisc_priv(sch);
unsigned int curband = q->curband;
struct Qdisc *qdisc;
struct sk_buff *skb;
int band;
for (band = 0; band < q->bands; band++) {
/* cycle through bands to ensure fairness */
curband++;
if (curband >= q->bands)
curband = 0;
/* Check that target subqueue is available before
* pulling an skb to avoid head-of-line blocking.
*/
if (!netif_xmit_stopped(
netdev_get_tx_queue(qdisc_dev(sch), curband))) {
qdisc = q->queues[curband];
skb = qdisc->ops->peek(qdisc);
if (skb)
return skb;
}
}
return NULL;
}
static void
multiq_reset(struct Qdisc *sch)
{
u16 band;
struct multiq_sched_data *q = qdisc_priv(sch);
for (band = 0; band < q->bands; band++)
qdisc_reset(q->queues[band]);
sch->q.qlen = 0;
q->curband = 0;
}
static void
multiq_destroy(struct Qdisc *sch)
{
int band;
struct multiq_sched_data *q = qdisc_priv(sch);
tcf_block_put(q->block);
for (band = 0; band < q->bands; band++)
qdisc_put(q->queues[band]);
kfree(q->queues);
}
static int multiq_tune(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct multiq_sched_data *q = qdisc_priv(sch);
struct tc_multiq_qopt *qopt;
net: sched: multiq: don't call qdisc_put() while holding tree lock Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG. Steps to reproduce for multiq: tc qdisc add dev ens1f0 root handle 1: multiq tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 ethtool -L ens1f0 combined 2 tc qdisc change dev ens1f0 root handle 1: multiq Resulting dmesg: [ 5539.419344] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 5539.420945] in_atomic(): 1, irqs_disabled(): 0, pid: 27658, name: tc [ 5539.422435] INFO: lockdep is turned off. [ 5539.423904] CPU: 21 PID: 27658 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 5539.425400] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5539.426911] Call Trace: [ 5539.428380] dump_stack+0x85/0xc0 [ 5539.429823] ___might_sleep.cold+0xac/0xbc [ 5539.431262] __mutex_lock+0x5b/0x960 [ 5539.432682] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.434103] ? __nla_validate_parse+0x51/0x840 [ 5539.435493] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.436903] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.438327] tcf_block_put_ext.part.0+0x21/0x50 [ 5539.439752] tcf_block_put+0x50/0x70 [ 5539.441165] sfq_destroy+0x15/0x50 [sch_sfq] [ 5539.442570] qdisc_destroy+0x5f/0x160 [ 5539.444000] multiq_tune+0x14a/0x420 [sch_multiq] [ 5539.445421] tc_modify_qdisc+0x324/0x840 [ 5539.446841] rtnetlink_rcv_msg+0x170/0x4b0 [ 5539.448269] ? netlink_deliver_tap+0x95/0x400 [ 5539.449691] ? rtnl_dellink+0x2d0/0x2d0 [ 5539.451116] netlink_rcv_skb+0x49/0x110 [ 5539.452522] netlink_unicast+0x171/0x200 [ 5539.453914] netlink_sendmsg+0x224/0x3f0 [ 5539.455304] sock_sendmsg+0x5e/0x60 [ 5539.456686] ___sys_sendmsg+0x2ae/0x330 [ 5539.458071] ? ___sys_recvmsg+0x159/0x1f0 [ 5539.459461] ? do_wp_page+0x9c/0x790 [ 5539.460846] ? __handle_mm_fault+0xcd3/0x19e0 [ 5539.462263] __sys_sendmsg+0x59/0xa0 [ 5539.463661] do_syscall_64+0x5c/0xb0 [ 5539.465044] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 5539.466454] RIP: 0033:0x7f1fe08177b8 [ 5539.467863] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 5539.470906] RSP: 002b:00007ffe812de5d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 5539.472483] RAX: ffffffffffffffda RBX: 000000005d8135e3 RCX: 00007f1fe08177b8 [ 5539.474069] RDX: 0000000000000000 RSI: 00007ffe812de640 RDI: 0000000000000003 [ 5539.475655] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000182e9b0 [ 5539.477203] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 5539.478699] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000 Rearrange locking in multiq_tune() in following ways: - In loop that removes Qdiscs from disabled queues, call qdisc_purge_queue() instead of qdisc_tree_flush_backlog() on Qdisc that is being destroyed. Save the Qdisc in temporary allocated array and call qdisc_put() on each element of the array after sch tree lock is released. This is safe to do because Qdiscs have already been reset by qdisc_purge_queue() inside sch tree lock critical section. - Do the same change for second loop that initializes Qdiscs for newly enabled queues in multiq_tune() function. Since sch tree lock is obtained and released on each iteration of this loop, just call qdisc_put() directly outside of critical section. Don't verify that old Qdisc is not noop_qdisc before releasing reference to it because such check is already performed by qdisc_put*() functions. Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-24 23:51:17 +08:00
struct Qdisc **removed;
int i, n_removed = 0;
if (!netif_is_multiqueue(qdisc_dev(sch)))
return -EOPNOTSUPP;
if (nla_len(opt) < sizeof(*qopt))
return -EINVAL;
qopt = nla_data(opt);
qopt->bands = qdisc_dev(sch)->real_num_tx_queues;
net: sched: multiq: don't call qdisc_put() while holding tree lock Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG. Steps to reproduce for multiq: tc qdisc add dev ens1f0 root handle 1: multiq tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 ethtool -L ens1f0 combined 2 tc qdisc change dev ens1f0 root handle 1: multiq Resulting dmesg: [ 5539.419344] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 5539.420945] in_atomic(): 1, irqs_disabled(): 0, pid: 27658, name: tc [ 5539.422435] INFO: lockdep is turned off. [ 5539.423904] CPU: 21 PID: 27658 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 5539.425400] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5539.426911] Call Trace: [ 5539.428380] dump_stack+0x85/0xc0 [ 5539.429823] ___might_sleep.cold+0xac/0xbc [ 5539.431262] __mutex_lock+0x5b/0x960 [ 5539.432682] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.434103] ? __nla_validate_parse+0x51/0x840 [ 5539.435493] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.436903] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.438327] tcf_block_put_ext.part.0+0x21/0x50 [ 5539.439752] tcf_block_put+0x50/0x70 [ 5539.441165] sfq_destroy+0x15/0x50 [sch_sfq] [ 5539.442570] qdisc_destroy+0x5f/0x160 [ 5539.444000] multiq_tune+0x14a/0x420 [sch_multiq] [ 5539.445421] tc_modify_qdisc+0x324/0x840 [ 5539.446841] rtnetlink_rcv_msg+0x170/0x4b0 [ 5539.448269] ? netlink_deliver_tap+0x95/0x400 [ 5539.449691] ? rtnl_dellink+0x2d0/0x2d0 [ 5539.451116] netlink_rcv_skb+0x49/0x110 [ 5539.452522] netlink_unicast+0x171/0x200 [ 5539.453914] netlink_sendmsg+0x224/0x3f0 [ 5539.455304] sock_sendmsg+0x5e/0x60 [ 5539.456686] ___sys_sendmsg+0x2ae/0x330 [ 5539.458071] ? ___sys_recvmsg+0x159/0x1f0 [ 5539.459461] ? do_wp_page+0x9c/0x790 [ 5539.460846] ? __handle_mm_fault+0xcd3/0x19e0 [ 5539.462263] __sys_sendmsg+0x59/0xa0 [ 5539.463661] do_syscall_64+0x5c/0xb0 [ 5539.465044] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 5539.466454] RIP: 0033:0x7f1fe08177b8 [ 5539.467863] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 5539.470906] RSP: 002b:00007ffe812de5d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 5539.472483] RAX: ffffffffffffffda RBX: 000000005d8135e3 RCX: 00007f1fe08177b8 [ 5539.474069] RDX: 0000000000000000 RSI: 00007ffe812de640 RDI: 0000000000000003 [ 5539.475655] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000182e9b0 [ 5539.477203] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 5539.478699] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000 Rearrange locking in multiq_tune() in following ways: - In loop that removes Qdiscs from disabled queues, call qdisc_purge_queue() instead of qdisc_tree_flush_backlog() on Qdisc that is being destroyed. Save the Qdisc in temporary allocated array and call qdisc_put() on each element of the array after sch tree lock is released. This is safe to do because Qdiscs have already been reset by qdisc_purge_queue() inside sch tree lock critical section. - Do the same change for second loop that initializes Qdiscs for newly enabled queues in multiq_tune() function. Since sch tree lock is obtained and released on each iteration of this loop, just call qdisc_put() directly outside of critical section. Don't verify that old Qdisc is not noop_qdisc before releasing reference to it because such check is already performed by qdisc_put*() functions. Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-24 23:51:17 +08:00
removed = kmalloc(sizeof(*removed) * (q->max_bands - q->bands),
GFP_KERNEL);
if (!removed)
return -ENOMEM;
sch_tree_lock(sch);
q->bands = qopt->bands;
for (i = q->bands; i < q->max_bands; i++) {
if (q->queues[i] != &noop_qdisc) {
struct Qdisc *child = q->queues[i];
q->queues[i] = &noop_qdisc;
net: sched: multiq: don't call qdisc_put() while holding tree lock Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG. Steps to reproduce for multiq: tc qdisc add dev ens1f0 root handle 1: multiq tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 ethtool -L ens1f0 combined 2 tc qdisc change dev ens1f0 root handle 1: multiq Resulting dmesg: [ 5539.419344] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 5539.420945] in_atomic(): 1, irqs_disabled(): 0, pid: 27658, name: tc [ 5539.422435] INFO: lockdep is turned off. [ 5539.423904] CPU: 21 PID: 27658 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 5539.425400] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5539.426911] Call Trace: [ 5539.428380] dump_stack+0x85/0xc0 [ 5539.429823] ___might_sleep.cold+0xac/0xbc [ 5539.431262] __mutex_lock+0x5b/0x960 [ 5539.432682] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.434103] ? __nla_validate_parse+0x51/0x840 [ 5539.435493] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.436903] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.438327] tcf_block_put_ext.part.0+0x21/0x50 [ 5539.439752] tcf_block_put+0x50/0x70 [ 5539.441165] sfq_destroy+0x15/0x50 [sch_sfq] [ 5539.442570] qdisc_destroy+0x5f/0x160 [ 5539.444000] multiq_tune+0x14a/0x420 [sch_multiq] [ 5539.445421] tc_modify_qdisc+0x324/0x840 [ 5539.446841] rtnetlink_rcv_msg+0x170/0x4b0 [ 5539.448269] ? netlink_deliver_tap+0x95/0x400 [ 5539.449691] ? rtnl_dellink+0x2d0/0x2d0 [ 5539.451116] netlink_rcv_skb+0x49/0x110 [ 5539.452522] netlink_unicast+0x171/0x200 [ 5539.453914] netlink_sendmsg+0x224/0x3f0 [ 5539.455304] sock_sendmsg+0x5e/0x60 [ 5539.456686] ___sys_sendmsg+0x2ae/0x330 [ 5539.458071] ? ___sys_recvmsg+0x159/0x1f0 [ 5539.459461] ? do_wp_page+0x9c/0x790 [ 5539.460846] ? __handle_mm_fault+0xcd3/0x19e0 [ 5539.462263] __sys_sendmsg+0x59/0xa0 [ 5539.463661] do_syscall_64+0x5c/0xb0 [ 5539.465044] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 5539.466454] RIP: 0033:0x7f1fe08177b8 [ 5539.467863] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 5539.470906] RSP: 002b:00007ffe812de5d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 5539.472483] RAX: ffffffffffffffda RBX: 000000005d8135e3 RCX: 00007f1fe08177b8 [ 5539.474069] RDX: 0000000000000000 RSI: 00007ffe812de640 RDI: 0000000000000003 [ 5539.475655] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000182e9b0 [ 5539.477203] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 5539.478699] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000 Rearrange locking in multiq_tune() in following ways: - In loop that removes Qdiscs from disabled queues, call qdisc_purge_queue() instead of qdisc_tree_flush_backlog() on Qdisc that is being destroyed. Save the Qdisc in temporary allocated array and call qdisc_put() on each element of the array after sch tree lock is released. This is safe to do because Qdiscs have already been reset by qdisc_purge_queue() inside sch tree lock critical section. - Do the same change for second loop that initializes Qdiscs for newly enabled queues in multiq_tune() function. Since sch tree lock is obtained and released on each iteration of this loop, just call qdisc_put() directly outside of critical section. Don't verify that old Qdisc is not noop_qdisc before releasing reference to it because such check is already performed by qdisc_put*() functions. Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-24 23:51:17 +08:00
qdisc_purge_queue(child);
removed[n_removed++] = child;
}
}
sch_tree_unlock(sch);
net: sched: multiq: don't call qdisc_put() while holding tree lock Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG. Steps to reproduce for multiq: tc qdisc add dev ens1f0 root handle 1: multiq tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 ethtool -L ens1f0 combined 2 tc qdisc change dev ens1f0 root handle 1: multiq Resulting dmesg: [ 5539.419344] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 5539.420945] in_atomic(): 1, irqs_disabled(): 0, pid: 27658, name: tc [ 5539.422435] INFO: lockdep is turned off. [ 5539.423904] CPU: 21 PID: 27658 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 5539.425400] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5539.426911] Call Trace: [ 5539.428380] dump_stack+0x85/0xc0 [ 5539.429823] ___might_sleep.cold+0xac/0xbc [ 5539.431262] __mutex_lock+0x5b/0x960 [ 5539.432682] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.434103] ? __nla_validate_parse+0x51/0x840 [ 5539.435493] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.436903] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.438327] tcf_block_put_ext.part.0+0x21/0x50 [ 5539.439752] tcf_block_put+0x50/0x70 [ 5539.441165] sfq_destroy+0x15/0x50 [sch_sfq] [ 5539.442570] qdisc_destroy+0x5f/0x160 [ 5539.444000] multiq_tune+0x14a/0x420 [sch_multiq] [ 5539.445421] tc_modify_qdisc+0x324/0x840 [ 5539.446841] rtnetlink_rcv_msg+0x170/0x4b0 [ 5539.448269] ? netlink_deliver_tap+0x95/0x400 [ 5539.449691] ? rtnl_dellink+0x2d0/0x2d0 [ 5539.451116] netlink_rcv_skb+0x49/0x110 [ 5539.452522] netlink_unicast+0x171/0x200 [ 5539.453914] netlink_sendmsg+0x224/0x3f0 [ 5539.455304] sock_sendmsg+0x5e/0x60 [ 5539.456686] ___sys_sendmsg+0x2ae/0x330 [ 5539.458071] ? ___sys_recvmsg+0x159/0x1f0 [ 5539.459461] ? do_wp_page+0x9c/0x790 [ 5539.460846] ? __handle_mm_fault+0xcd3/0x19e0 [ 5539.462263] __sys_sendmsg+0x59/0xa0 [ 5539.463661] do_syscall_64+0x5c/0xb0 [ 5539.465044] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 5539.466454] RIP: 0033:0x7f1fe08177b8 [ 5539.467863] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 5539.470906] RSP: 002b:00007ffe812de5d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 5539.472483] RAX: ffffffffffffffda RBX: 000000005d8135e3 RCX: 00007f1fe08177b8 [ 5539.474069] RDX: 0000000000000000 RSI: 00007ffe812de640 RDI: 0000000000000003 [ 5539.475655] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000182e9b0 [ 5539.477203] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 5539.478699] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000 Rearrange locking in multiq_tune() in following ways: - In loop that removes Qdiscs from disabled queues, call qdisc_purge_queue() instead of qdisc_tree_flush_backlog() on Qdisc that is being destroyed. Save the Qdisc in temporary allocated array and call qdisc_put() on each element of the array after sch tree lock is released. This is safe to do because Qdiscs have already been reset by qdisc_purge_queue() inside sch tree lock critical section. - Do the same change for second loop that initializes Qdiscs for newly enabled queues in multiq_tune() function. Since sch tree lock is obtained and released on each iteration of this loop, just call qdisc_put() directly outside of critical section. Don't verify that old Qdisc is not noop_qdisc before releasing reference to it because such check is already performed by qdisc_put*() functions. Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-24 23:51:17 +08:00
for (i = 0; i < n_removed; i++)
qdisc_put(removed[i]);
kfree(removed);
for (i = 0; i < q->bands; i++) {
if (q->queues[i] == &noop_qdisc) {
struct Qdisc *child, *old;
child = qdisc_create_dflt(sch->dev_queue,
&pfifo_qdisc_ops,
TC_H_MAKE(sch->handle,
i + 1), extack);
if (child) {
sch_tree_lock(sch);
old = q->queues[i];
q->queues[i] = child;
if (child != &noop_qdisc)
qdisc_hash_add(child, true);
net: sched: multiq: don't call qdisc_put() while holding tree lock Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG. Steps to reproduce for multiq: tc qdisc add dev ens1f0 root handle 1: multiq tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 ethtool -L ens1f0 combined 2 tc qdisc change dev ens1f0 root handle 1: multiq Resulting dmesg: [ 5539.419344] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 5539.420945] in_atomic(): 1, irqs_disabled(): 0, pid: 27658, name: tc [ 5539.422435] INFO: lockdep is turned off. [ 5539.423904] CPU: 21 PID: 27658 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 5539.425400] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5539.426911] Call Trace: [ 5539.428380] dump_stack+0x85/0xc0 [ 5539.429823] ___might_sleep.cold+0xac/0xbc [ 5539.431262] __mutex_lock+0x5b/0x960 [ 5539.432682] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.434103] ? __nla_validate_parse+0x51/0x840 [ 5539.435493] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.436903] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.438327] tcf_block_put_ext.part.0+0x21/0x50 [ 5539.439752] tcf_block_put+0x50/0x70 [ 5539.441165] sfq_destroy+0x15/0x50 [sch_sfq] [ 5539.442570] qdisc_destroy+0x5f/0x160 [ 5539.444000] multiq_tune+0x14a/0x420 [sch_multiq] [ 5539.445421] tc_modify_qdisc+0x324/0x840 [ 5539.446841] rtnetlink_rcv_msg+0x170/0x4b0 [ 5539.448269] ? netlink_deliver_tap+0x95/0x400 [ 5539.449691] ? rtnl_dellink+0x2d0/0x2d0 [ 5539.451116] netlink_rcv_skb+0x49/0x110 [ 5539.452522] netlink_unicast+0x171/0x200 [ 5539.453914] netlink_sendmsg+0x224/0x3f0 [ 5539.455304] sock_sendmsg+0x5e/0x60 [ 5539.456686] ___sys_sendmsg+0x2ae/0x330 [ 5539.458071] ? ___sys_recvmsg+0x159/0x1f0 [ 5539.459461] ? do_wp_page+0x9c/0x790 [ 5539.460846] ? __handle_mm_fault+0xcd3/0x19e0 [ 5539.462263] __sys_sendmsg+0x59/0xa0 [ 5539.463661] do_syscall_64+0x5c/0xb0 [ 5539.465044] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 5539.466454] RIP: 0033:0x7f1fe08177b8 [ 5539.467863] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 5539.470906] RSP: 002b:00007ffe812de5d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 5539.472483] RAX: ffffffffffffffda RBX: 000000005d8135e3 RCX: 00007f1fe08177b8 [ 5539.474069] RDX: 0000000000000000 RSI: 00007ffe812de640 RDI: 0000000000000003 [ 5539.475655] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000182e9b0 [ 5539.477203] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 5539.478699] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000 Rearrange locking in multiq_tune() in following ways: - In loop that removes Qdiscs from disabled queues, call qdisc_purge_queue() instead of qdisc_tree_flush_backlog() on Qdisc that is being destroyed. Save the Qdisc in temporary allocated array and call qdisc_put() on each element of the array after sch tree lock is released. This is safe to do because Qdiscs have already been reset by qdisc_purge_queue() inside sch tree lock critical section. - Do the same change for second loop that initializes Qdiscs for newly enabled queues in multiq_tune() function. Since sch tree lock is obtained and released on each iteration of this loop, just call qdisc_put() directly outside of critical section. Don't verify that old Qdisc is not noop_qdisc before releasing reference to it because such check is already performed by qdisc_put*() functions. Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-24 23:51:17 +08:00
if (old != &noop_qdisc)
qdisc_purge_queue(old);
sch_tree_unlock(sch);
net: sched: multiq: don't call qdisc_put() while holding tree lock Recent changes that removed rtnl dependency from rules update path of tc also made tcf_block_put() function sleeping. This function is called from ops->destroy() of several Qdisc implementations, which in turn is called by qdisc_put(). Some Qdiscs call qdisc_put() while holding sch tree spinlock, which results sleeping-while-atomic BUG. Steps to reproduce for multiq: tc qdisc add dev ens1f0 root handle 1: multiq tc qdisc add dev ens1f0 parent 1:10 handle 50: sfq perturb 10 ethtool -L ens1f0 combined 2 tc qdisc change dev ens1f0 root handle 1: multiq Resulting dmesg: [ 5539.419344] BUG: sleeping function called from invalid context at kernel/locking/mutex.c:909 [ 5539.420945] in_atomic(): 1, irqs_disabled(): 0, pid: 27658, name: tc [ 5539.422435] INFO: lockdep is turned off. [ 5539.423904] CPU: 21 PID: 27658 Comm: tc Tainted: G W 5.3.0-rc8+ #721 [ 5539.425400] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017 [ 5539.426911] Call Trace: [ 5539.428380] dump_stack+0x85/0xc0 [ 5539.429823] ___might_sleep.cold+0xac/0xbc [ 5539.431262] __mutex_lock+0x5b/0x960 [ 5539.432682] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.434103] ? __nla_validate_parse+0x51/0x840 [ 5539.435493] ? tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.436903] tcf_chain0_head_change_cb_del.isra.0+0x1b/0xf0 [ 5539.438327] tcf_block_put_ext.part.0+0x21/0x50 [ 5539.439752] tcf_block_put+0x50/0x70 [ 5539.441165] sfq_destroy+0x15/0x50 [sch_sfq] [ 5539.442570] qdisc_destroy+0x5f/0x160 [ 5539.444000] multiq_tune+0x14a/0x420 [sch_multiq] [ 5539.445421] tc_modify_qdisc+0x324/0x840 [ 5539.446841] rtnetlink_rcv_msg+0x170/0x4b0 [ 5539.448269] ? netlink_deliver_tap+0x95/0x400 [ 5539.449691] ? rtnl_dellink+0x2d0/0x2d0 [ 5539.451116] netlink_rcv_skb+0x49/0x110 [ 5539.452522] netlink_unicast+0x171/0x200 [ 5539.453914] netlink_sendmsg+0x224/0x3f0 [ 5539.455304] sock_sendmsg+0x5e/0x60 [ 5539.456686] ___sys_sendmsg+0x2ae/0x330 [ 5539.458071] ? ___sys_recvmsg+0x159/0x1f0 [ 5539.459461] ? do_wp_page+0x9c/0x790 [ 5539.460846] ? __handle_mm_fault+0xcd3/0x19e0 [ 5539.462263] __sys_sendmsg+0x59/0xa0 [ 5539.463661] do_syscall_64+0x5c/0xb0 [ 5539.465044] entry_SYSCALL_64_after_hwframe+0x49/0xbe [ 5539.466454] RIP: 0033:0x7f1fe08177b8 [ 5539.467863] Code: 89 02 48 c7 c0 ff ff ff ff eb bb 0f 1f 80 00 00 00 00 f3 0f 1e fa 48 8d 05 65 8f 0c 00 8b 00 85 c0 75 17 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 58 c3 0f 1f 80 00 00 00 00 48 83 ec 28 89 5 4 [ 5539.470906] RSP: 002b:00007ffe812de5d8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e [ 5539.472483] RAX: ffffffffffffffda RBX: 000000005d8135e3 RCX: 00007f1fe08177b8 [ 5539.474069] RDX: 0000000000000000 RSI: 00007ffe812de640 RDI: 0000000000000003 [ 5539.475655] RBP: 0000000000000000 R08: 0000000000000001 R09: 000000000182e9b0 [ 5539.477203] R10: 0000000000404eda R11: 0000000000000246 R12: 0000000000000001 [ 5539.478699] R13: 000000000047f640 R14: 0000000000000000 R15: 0000000000000000 Rearrange locking in multiq_tune() in following ways: - In loop that removes Qdiscs from disabled queues, call qdisc_purge_queue() instead of qdisc_tree_flush_backlog() on Qdisc that is being destroyed. Save the Qdisc in temporary allocated array and call qdisc_put() on each element of the array after sch tree lock is released. This is safe to do because Qdiscs have already been reset by qdisc_purge_queue() inside sch tree lock critical section. - Do the same change for second loop that initializes Qdiscs for newly enabled queues in multiq_tune() function. Since sch tree lock is obtained and released on each iteration of this loop, just call qdisc_put() directly outside of critical section. Don't verify that old Qdisc is not noop_qdisc before releasing reference to it because such check is already performed by qdisc_put*() functions. Fixes: c266f64dbfa2 ("net: sched: protect block state with mutex") Signed-off-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2019-09-24 23:51:17 +08:00
qdisc_put(old);
}
}
}
return 0;
}
static int multiq_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct multiq_sched_data *q = qdisc_priv(sch);
int i, err;
q->queues = NULL;
if (!opt)
return -EINVAL;
err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
if (err)
return err;
q->max_bands = qdisc_dev(sch)->num_tx_queues;
q->queues = kcalloc(q->max_bands, sizeof(struct Qdisc *), GFP_KERNEL);
if (!q->queues)
return -ENOBUFS;
for (i = 0; i < q->max_bands; i++)
q->queues[i] = &noop_qdisc;
return multiq_tune(sch, opt, extack);
}
static int multiq_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct multiq_sched_data *q = qdisc_priv(sch);
unsigned char *b = skb_tail_pointer(skb);
struct tc_multiq_qopt opt;
opt.bands = q->bands;
opt.max_bands = q->max_bands;
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
return skb->len;
nla_put_failure:
nlmsg_trim(skb, b);
return -1;
}
static int multiq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
struct Qdisc **old, struct netlink_ext_ack *extack)
{
struct multiq_sched_data *q = qdisc_priv(sch);
unsigned long band = arg - 1;
if (new == NULL)
new = &noop_qdisc;
*old = qdisc_replace(sch, new, &q->queues[band]);
return 0;
}
static struct Qdisc *
multiq_leaf(struct Qdisc *sch, unsigned long arg)
{
struct multiq_sched_data *q = qdisc_priv(sch);
unsigned long band = arg - 1;
return q->queues[band];
}
static unsigned long multiq_find(struct Qdisc *sch, u32 classid)
{
struct multiq_sched_data *q = qdisc_priv(sch);
unsigned long band = TC_H_MIN(classid);
if (band - 1 >= q->bands)
return 0;
return band;
}
static unsigned long multiq_bind(struct Qdisc *sch, unsigned long parent,
u32 classid)
{
return multiq_find(sch, classid);
}
static void multiq_unbind(struct Qdisc *q, unsigned long cl)
{
}
static int multiq_dump_class(struct Qdisc *sch, unsigned long cl,
struct sk_buff *skb, struct tcmsg *tcm)
{
struct multiq_sched_data *q = qdisc_priv(sch);
tcm->tcm_handle |= TC_H_MIN(cl);
tcm->tcm_info = q->queues[cl - 1]->handle;
return 0;
}
static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
struct gnet_dump *d)
{
struct multiq_sched_data *q = qdisc_priv(sch);
struct Qdisc *cl_q;
cl_q = q->queues[cl - 1];
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch),
d, cl_q->cpu_bstats, &cl_q->bstats) < 0 ||
qdisc_qstats_copy(d, cl_q) < 0)
return -1;
return 0;
}
static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
struct multiq_sched_data *q = qdisc_priv(sch);
int band;
if (arg->stop)
return;
for (band = 0; band < q->bands; band++) {
if (arg->count < arg->skip) {
arg->count++;
continue;
}
if (arg->fn(sch, band + 1, arg) < 0) {
arg->stop = 1;
break;
}
arg->count++;
}
}
static struct tcf_block *multiq_tcf_block(struct Qdisc *sch, unsigned long cl,
struct netlink_ext_ack *extack)
{
struct multiq_sched_data *q = qdisc_priv(sch);
if (cl)
return NULL;
return q->block;
}
static const struct Qdisc_class_ops multiq_class_ops = {
.graft = multiq_graft,
.leaf = multiq_leaf,
.find = multiq_find,
.walk = multiq_walk,
.tcf_block = multiq_tcf_block,
.bind_tcf = multiq_bind,
.unbind_tcf = multiq_unbind,
.dump = multiq_dump_class,
.dump_stats = multiq_dump_class_stats,
};
static struct Qdisc_ops multiq_qdisc_ops __read_mostly = {
.next = NULL,
.cl_ops = &multiq_class_ops,
.id = "multiq",
.priv_size = sizeof(struct multiq_sched_data),
.enqueue = multiq_enqueue,
.dequeue = multiq_dequeue,
.peek = multiq_peek,
.init = multiq_init,
.reset = multiq_reset,
.destroy = multiq_destroy,
.change = multiq_tune,
.dump = multiq_dump,
.owner = THIS_MODULE,
};
static int __init multiq_module_init(void)
{
return register_qdisc(&multiq_qdisc_ops);
}
static void __exit multiq_module_exit(void)
{
unregister_qdisc(&multiq_qdisc_ops);
}
module_init(multiq_module_init)
module_exit(multiq_module_exit)
MODULE_LICENSE("GPL");