/* * 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); thorNicolai Stange <nicstange@gmail.com>2016-12-07 22:21:33 +0100 committerTejun Heo <tj@kernel.org>2016-12-07 16:29:09 -0500 commite185934ff94466b4a449165e5f1c164a44d005f2 (patch) treec773d05d4c72292e3babd4ce1a8bd56d965ebb4c /include/uapi parent5c3ef39738f74a3759918cc1a1ad099504f9d1b7 (diff)
libata-scsi: disable SCT Write Same for the moment
SCT Write Same support had been introduced with commit 7b2030942859 ("libata: Add support for SCT Write Same") Some problems, namely excessive userspace segfaults, had been reported at http://lkml.kernel.org/r/20160908192736.GA4356@gmail.com This lead to commit 0ce1b18c42a5 ("libata: Some drives failing on SCT Write Same") which strived to disable SCT Write Same on !ZAC devices. Due to the way this was done and to the logic in sd_config_write_same(), this didn't work for those devices that have ->max_ws_blocks > SD_MAX_WS10_BLOCKS: for these, ->no_write_same and ->max_write_same_sectors would still be non-zero, but ->ws10 == ->ws16 == 0. This would cause sd_setup_write_same_cmnd() to demultiplex REQ_OP_WRITE_SAME requests to WRITE_SAME, and these in turn aren't supported by libata-scsi: EXT4-fs (dm-1): Delayed block allocation failed for inode 2625094 at logical offset 2032 with max blocks 2 with error 121 EXT4-fs (dm-1): This should not happen!! Data will be lost 121 == EREMOTEIO is what scsi_io_completion() asserts in case of invalid opcodes. Back to the original problem of userspace segfaults: this can be tracked down to ata_format_sct_write_same() overwriting the input page. Sometimes, this page is ZERO_PAGE(0) which ceases to be filled with zeros from that point on. Since ZERO_PAGE(0) is used for userspace .bss mappings, code of the following is doomed: static char *a = NULL; /* .bss */ ... if (a) *a = 'a'; This problem is not solved by disabling SCT Write Same for !ZAC devices only. It can certainly be fixed, but the final release is quite close -- so disable SCT Write Same for all ATA devices rather than introducing some SCT key buffer allocation schemes at this point. Fixes: 7b2030942859 ("libata: Add support for SCT Write Same") Signed-off-by: Nicolai Stange <nicstange@gmail.com> Signed-off-by: Tejun Heo <tj@kernel.org>
Diffstat (limited to 'include/uapi')