/* * net/sched/sch_fifo.c The simplest FIFO queue. * * 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, */ #include #include #include #include #include #include #include /* 1 band FIFO pseudo-"scheduler" */ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { if (likely(sch->qstats.backlog + qdisc_pkt_len(skb) <= sch->limit)) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); } static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { if (likely(sch->q.qlen < sch->limit)) return qdisc_enqueue_tail(skb, sch); return qdisc_drop(skb, sch, to_free); } static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { unsigned int prev_backlog; if (likely(sch->q.qlen < sch->limit)) return qdisc_enqueue_tail(skb, sch); prev_backlog = sch->qstats.backlog; /* queue full, remove one skb to fulfill the limit */ __qdisc_queue_drop_head(sch, &sch->q, to_free); qdisc_qstats_drop(sch); qdisc_enqueue_tail(skb, sch); qdisc_tree_reduce_backlog(sch, 0, prev_backlog - sch->qstats.backlog); return NET_XMIT_CN; } static int fifo_init(struct Qdisc *sch, struct nlattr *opt) { bool bypass; bool is_bfifo = sch->ops == &bfifo_qdisc_ops; if (opt == NULL) { u32 limit = qdisc_dev(sch)->tx_queue_len; if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); sch->limit = limit; } else { struct tc_fifo_qopt *ctl = nla_data(opt); if (nla_len(opt) < sizeof(*ctl)) return -EINVAL; sch->limit = ctl->limit; } if (is_bfifo) bypass = sch->limit >= psched_mtu(qdisc_dev(sch)); else bypass = sch->limit >= 1; if (bypass) sch->flags |= TCQ_F_CAN_BYPASS; else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } static int fifo_dump(struct Qdisc *sch, struct sk_buff *skb) { struct tc_fifo_qopt opt = { .limit = sch->limit }; if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } struct Qdisc_ops pfifo_qdisc_ops __read_mostly = { .id = "pfifo", .priv_size = 0, .enqueue = pfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, }; EXPORT_SYMBOL(pfifo_qdisc_ops); struct Qdisc_ops bfifo_qdisc_ops __read_mostly = { .id = "bfifo", .priv_size = 0, .enqueue = bfifo_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, }; EXPORT_SYMBOL(bfifo_qdisc_ops); struct Qdisc_ops pfifo_head_drop_qdisc_ops __read_mostly = { .id = "pfifo_head_drop", .priv_size = 0, .enqueue = pfifo_tail_enqueue, .dequeue = qdisc_dequeue_head, .peek = qdisc_peek_head, .init = fifo_init, .reset = qdisc_reset_queue, .change = fifo_init, .dump = fifo_dump, .owner = THIS_MODULE, }; /* Pass size change message down to embedded FIFO */ int fifo_set_limit(struct Qdisc *q, unsigned int limit) { struct nlattr *nla; int ret = -ENOMEM; /* Hack to avoid sending change message to non-FIFO */ if (strncmp(q->ops->id + 1, "fifo", 4) != 0) return 0; nla = kmalloc(nla_attr_size(sizeof(struct tc_fifo_qopt)), GFP_KERNEL); if (nla) { nla->nla_type = RTM_NEWQDISC; nla->nla_len = nla_attr_size(sizeof(struct tc_fifo_qopt)); ((struct tc_fifo_qopt *)nla_data(nla))->limit = limit; ret = q->ops->change(q, nla); kfree(nla); } return ret; } EXPORT_SYMBOL(fifo_set_limit); struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, unsigned int limit) { struct Qdisc *q; int err = -ENOMEM; q = qdisc_create_dflt(sch->dev_queue, ops, TC_H_MAKE(sch->handle, 1)); if (q) { err = fifo_set_limit(q, limit); if (err < 0) { qdisc_destroy(q); q = NULL; } } return q ? : ERR_PTR(err); } EXPORT_SYMBOL(fifo_create_dflt); this.form.submit();'>
authorDouglas Miller <dougmill@linux.vnet.ibm.com>2017-01-28 06:42:20 -0600
committerTejun Heo <tj@kernel.org>2017-01-28 07:49:42 -0500
commit966d2b04e070bc040319aaebfec09e0144dc3341 (patch)
tree4b96156e3d1dd4dfd6039b7c219c9dc4616da52d /fs/xfs/libxfs/xfs_cksum.h
parent1b1bc42c1692e9b62756323c675a44cb1a1f9dbd (diff)
percpu-refcount: fix reference leak during percpu-atomic transition
percpu_ref_tryget() and percpu_ref_tryget_live() should return "true" IFF they acquire a reference. But the return value from atomic_long_inc_not_zero() is a long and may have high bits set, e.g. PERCPU_COUNT_BIAS, and the return value of the tryget routines is bool so the reference may actually be acquired but the routines return "false" which results in a reference leak since the caller assumes it does not need to do a corresponding percpu_ref_put(). This was seen when performing CPU hotplug during I/O, as hangs in blk_mq_freeze_queue_wait where percpu_ref_kill (blk_mq_freeze_queue_start) raced with percpu_ref_tryget (blk_mq_timeout_work). Sample stack trace: __switch_to+0x2c0/0x450 __schedule+0x2f8/0x970 schedule+0x48/0xc0 blk_mq_freeze_queue_wait+0x94/0x120 blk_mq_queue_reinit_work+0xb8/0x180 blk_mq_queue_reinit_prepare+0x84/0xa0 cpuhp_invoke_callback+0x17c/0x600 cpuhp_up_callbacks+0x58/0x150 _cpu_up+0xf0/0x1c0 do_cpu_up+0x120/0x150 cpu_subsys_online+0x64/0xe0 device_online+0xb4/0x120 online_store+0xb4/0xc0 dev_attr_store+0x68/0xa0 sysfs_kf_write+0x80/0xb0 kernfs_fop_write+0x17c/0x250 __vfs_write+0x6c/0x1e0 vfs_write+0xd0/0x270 SyS_write+0x6c/0x110 system_call+0x38/0xe0 Examination of the queue showed a single reference (no PERCPU_COUNT_BIAS, and __PERCPU_REF_DEAD, __PERCPU_REF_ATOMIC set) and no requests. However, conditions at the time of the race are count of PERCPU_COUNT_BIAS + 0 and __PERCPU_REF_DEAD and __PERCPU_REF_ATOMIC set. The fix is to make the tryget routines use an actual boolean internally instead of the atomic long result truncated to a int. Fixes: e625305b3907 percpu-refcount: make percpu_ref based on longs instead of ints Link: https://bugzilla.kernel.org/show_bug.cgi?id=190751 Signed-off-by: Douglas Miller <dougmill@linux.vnet.ibm.com> Reviewed-by: Jens Axboe <axboe@fb.com> Signed-off-by: Tejun Heo <tj@kernel.org> Fixes: e625305b3907 ("percpu-refcount: make percpu_ref based on longs instead of ints") Cc: stable@vger.kernel.org # v3.18+
Diffstat (limited to 'fs/xfs/libxfs/xfs_cksum.h')