From bbb4c4323a4d9cb5ca04db904aa3050a7586839a Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 4 Oct 2018 14:27:55 +0100 Subject: dns: Allow the dns resolver to retrieve a server set Allow the DNS resolver to retrieve a set of servers and their associated addresses, ports, preference and weight ratings. In terms of communication with userspace, "srv=1" is added to the callout string (the '1' indicating the maximum data version supported by the kernel) to ask the userspace side for this. If the userspace side doesn't recognise it, it will ignore the option and return the usual text address list. If the userspace side does recognise it, it will return some binary data that begins with a zero byte that would cause the string parsers to give an error. The second byte contains the version of the data in the blob (this may be between 1 and the version specified in the callout data). The remainder of the payload is version-specific. In version 1, the payload looks like (note that this is packed): u8 Non-string marker (ie. 0) u8 Content (0 => Server list) u8 Version (ie. 1) u8 Source (eg. DNS_RECORD_FROM_DNS_SRV) u8 Status (eg. DNS_LOOKUP_GOOD) u8 Number of servers foreach-server { u16 Name length (LE) u16 Priority (as per SRV record) (LE) u16 Weight (as per SRV record) (LE) u16 Port (LE) u8 Source (eg. DNS_RECORD_FROM_NSS) u8 Status (eg. DNS_LOOKUP_GOT_NOT_FOUND) u8 Protocol (eg. DNS_SERVER_PROTOCOL_UDP) u8 Number of addresses char[] Name (not NUL-terminated) foreach-address { u8 Family (AF_INET{,6}) union { u8[4] ipv4_addr u8[16] ipv6_addr } } } This can then be used to fetch a whole cell's VL-server configuration for AFS, for example. Signed-off-by: David Howells Signed-off-by: David S. Miller --- include/uapi/linux/dns_resolver.h | 116 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 include/uapi/linux/dns_resolver.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dns_resolver.h b/include/uapi/linux/dns_resolver.h new file mode 100644 index 000000000000..129745f9c794 --- /dev/null +++ b/include/uapi/linux/dns_resolver.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* DNS resolver interface definitions. + * + * Copyright (C) 2018 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _UAPI_LINUX_DNS_RESOLVER_H +#define _UAPI_LINUX_DNS_RESOLVER_H + +#include + +/* + * Type of payload. + */ +enum dns_payload_content_type { + DNS_PAYLOAD_IS_SERVER_LIST = 0, /* List of servers, requested by srv=1 */ +}; + +/* + * Type of address that might be found in an address record. + */ +enum dns_payload_address_type { + DNS_ADDRESS_IS_IPV4 = 0, /* 4-byte AF_INET address */ + DNS_ADDRESS_IS_IPV6 = 1, /* 16-byte AF_INET6 address */ +}; + +/* + * Type of protocol used to access a server. + */ +enum dns_payload_protocol_type { + DNS_SERVER_PROTOCOL_UNSPECIFIED = 0, + DNS_SERVER_PROTOCOL_UDP = 1, /* Use UDP to talk to the server */ + DNS_SERVER_PROTOCOL_TCP = 2, /* Use TCP to talk to the server */ +}; + +/* + * Source of record included in DNS resolver payload. + */ +enum dns_record_source { + DNS_RECORD_UNAVAILABLE = 0, /* No source available (empty record) */ + DNS_RECORD_FROM_CONFIG = 1, /* From local configuration data */ + DNS_RECORD_FROM_DNS_A = 2, /* From DNS A or AAAA record */ + DNS_RECORD_FROM_DNS_AFSDB = 3, /* From DNS AFSDB record */ + DNS_RECORD_FROM_DNS_SRV = 4, /* From DNS SRV record */ + DNS_RECORD_FROM_NSS = 5, /* From NSS */ + NR__dns_record_source +}; + +/* + * Status of record included in DNS resolver payload. + */ +enum dns_lookup_status { + DNS_LOOKUP_NOT_DONE = 0, /* No lookup has been made */ + DNS_LOOKUP_GOOD = 1, /* Good records obtained */ + DNS_LOOKUP_GOOD_WITH_BAD = 2, /* Good records, some decoding errors */ + DNS_LOOKUP_BAD = 3, /* Couldn't decode results */ + DNS_LOOKUP_GOT_NOT_FOUND = 4, /* Got a "Not Found" result */ + DNS_LOOKUP_GOT_LOCAL_FAILURE = 5, /* Local failure during lookup */ + DNS_LOOKUP_GOT_TEMP_FAILURE = 6, /* Temporary failure during lookup */ + DNS_LOOKUP_GOT_NS_FAILURE = 7, /* Name server failure */ + NR__dns_lookup_status +}; + +/* + * Header at the beginning of binary format payload. + */ +struct dns_payload_header { + __u8 zero; /* Zero byte: marks this as not being text */ + __u8 content; /* enum dns_payload_content_type */ + __u8 version; /* Encoding version */ +} __packed; + +/* + * Header at the beginning of a V1 server list. This is followed directly by + * the server records. Each server records begins with a struct of type + * dns_server_list_v1_server. + */ +struct dns_server_list_v1_header { + struct dns_payload_header hdr; + __u8 source; /* enum dns_record_source */ + __u8 status; /* enum dns_lookup_status */ + __u8 nr_servers; /* Number of server records following this */ +} __packed; + +/* + * Header at the beginning of each V1 server record. This is followed by the + * characters of the name with no NUL-terminator, followed by the address + * records for that server. Each address record begins with a struct of type + * struct dns_server_list_v1_address. + */ +struct dns_server_list_v1_server { + __u16 name_len; /* Length of name (LE) */ + __u16 priority; /* Priority (as SRV record) (LE) */ + __u16 weight; /* Weight (as SRV record) (LE) */ + __u16 port; /* UDP/TCP port number (LE) */ + __u8 source; /* enum dns_record_source */ + __u8 status; /* enum dns_lookup_status */ + __u8 protocol; /* enum dns_payload_protocol_type */ + __u8 nr_addrs; +} __packed; + +/* + * Header at the beginning of each V1 address record. This is followed by the + * bytes of the address, 4 for IPV4 and 16 for IPV6. + */ +struct dns_server_list_v1_address { + __u8 address_type; /* enum dns_payload_address_type */ +} __packed; + +#endif /* _UAPI_LINUX_DNS_RESOLVER_H */ -- cgit v1.2.3 From 5a781ccbd19e4664babcbe4b4ead7aa2b9283d22 Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Fri, 28 Sep 2018 17:59:43 -0700 Subject: tc: Add support for configuring the taprio scheduler This traffic scheduler allows traffic classes states (transmission allowed/not allowed, in the simplest case) to be scheduled, according to a pre-generated time sequence. This is the basis of the IEEE 802.1Qbv specification. Example configuration: tc qdisc replace dev enp3s0 parent root handle 100 taprio \ num_tc 3 \ map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 \ queues 1@0 1@1 2@2 \ base-time 1528743495910289987 \ sched-entry S 01 300000 \ sched-entry S 02 300000 \ sched-entry S 04 300000 \ clockid CLOCK_TAI The configuration format is similar to mqprio. The main difference is the presence of a schedule, built by multiple "sched-entry" definitions, each entry has the following format: sched-entry The only supported is "S", which means "SetGateStates", following the IEEE 802.1Qbv-2015 definition (Table 8-6). is a bitmask where each bit is a associated with a traffic class, so bit 0 (the least significant bit) being "on" means that traffic class 0 is "active" for that schedule entry. is a time duration in nanoseconds that specifies for how long that state defined by and should be held before moving to the next entry. This schedule is circular, that is, after the last entry is executed it starts from the first one, indefinitely. The other parameters can be defined as follows: - base-time: specifies the instant when the schedule starts, if 'base-time' is a time in the past, the schedule will start at base-time + (N * cycle-time) where N is the smallest integer so the resulting time is greater than "now", and "cycle-time" is the sum of all the intervals of the entries in the schedule; - clockid: specifies the reference clock to be used; The parameters should be similar to what the IEEE 802.1Q family of specification defines. Signed-off-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- include/uapi/linux/pkt_sched.h | 46 ++ net/sched/Kconfig | 11 + net/sched/Makefile | 1 + net/sched/sch_taprio.c | 962 +++++++++++++++++++++++++++++++++++++++++ 4 files changed, 1020 insertions(+) create mode 100644 net/sched/sch_taprio.c (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index e9b7244ac381..89ee47c2f17d 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -1084,4 +1084,50 @@ enum { CAKE_ATM_MAX }; + +/* TAPRIO */ +enum { + TC_TAPRIO_CMD_SET_GATES = 0x00, + TC_TAPRIO_CMD_SET_AND_HOLD = 0x01, + TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02, +}; + +enum { + TCA_TAPRIO_SCHED_ENTRY_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */ + TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */ + __TCA_TAPRIO_SCHED_ENTRY_MAX, +}; +#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1) + +/* The format for schedule entry list is: + * [TCA_TAPRIO_SCHED_ENTRY_LIST] + * [TCA_TAPRIO_SCHED_ENTRY] + * [TCA_TAPRIO_SCHED_ENTRY_CMD] + * [TCA_TAPRIO_SCHED_ENTRY_GATES] + * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] + */ +enum { + TCA_TAPRIO_SCHED_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY, + __TCA_TAPRIO_SCHED_MAX, +}; + +#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1) + +enum { + TCA_TAPRIO_ATTR_UNSPEC, + TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ + TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */ + TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */ + TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */ + TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */ + TCA_TAPRIO_PAD, + __TCA_TAPRIO_ATTR_MAX, +}; + +#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1) + #endif diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e95741388311..1b9afdee5ba9 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -194,6 +194,17 @@ config NET_SCH_ETF To compile this code as a module, choose M here: the module will be called sch_etf. +config NET_SCH_TAPRIO + tristate "Time Aware Priority (taprio) Scheduler" + help + Say Y here if you want to use the Time Aware Priority (taprio) packet + scheduling algorithm. + + See the top of for more details. + + To compile this code as a module, choose M here: the + module will be called sch_taprio. + config NET_SCH_GRED tristate "Generic Random Early Detection (GRED)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index f0403f49edcb..8a40431d7b5c 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -57,6 +57,7 @@ obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o obj-$(CONFIG_NET_SCH_ETF) += sch_etf.o +obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c new file mode 100644 index 000000000000..206e4dbed12f --- /dev/null +++ b/net/sched/sch_taprio.c @@ -0,0 +1,962 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* net/sched/sch_taprio.c Time Aware Priority Scheduler + * + * Authors: Vinicius Costa Gomes + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define TAPRIO_ALL_GATES_OPEN -1 + +struct sched_entry { + struct list_head list; + + /* The instant that this entry "closes" and the next one + * should open, the qdisc will make some effort so that no + * packet leaves after this time. + */ + ktime_t close_time; + atomic_t budget; + int index; + u32 gate_mask; + u32 interval; + u8 command; +}; + +struct taprio_sched { + struct Qdisc **qdiscs; + struct Qdisc *root; + s64 base_time; + int clockid; + int picos_per_byte; /* Using picoseconds because for 10Gbps+ + * speeds it's sub-nanoseconds per byte + */ + size_t num_entries; + + /* Protects the update side of the RCU protected current_entry */ + spinlock_t current_entry_lock; + struct sched_entry __rcu *current_entry; + struct list_head entries; + ktime_t (*get_time)(void); + struct hrtimer advance_timer; +}; + +static int taprio_enqueue(struct sk_buff *skb, struct Qdisc *sch, + struct sk_buff **to_free) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct Qdisc *child; + int queue; + + queue = skb_get_queue_mapping(skb); + + child = q->qdiscs[queue]; + if (unlikely(!child)) + return qdisc_drop(skb, sch, to_free); + + qdisc_qstats_backlog_inc(sch, skb); + sch->q.qlen++; + + return qdisc_enqueue(skb, child, to_free); +} + +static struct sk_buff *taprio_peek(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry; + struct sk_buff *skb; + u32 gate_mask; + int i; + + rcu_read_lock(); + entry = rcu_dereference(q->current_entry); + gate_mask = entry ? entry->gate_mask : -1; + rcu_read_unlock(); + + if (!gate_mask) + return NULL; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + int prio; + u8 tc; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); + + if (!(gate_mask & BIT(tc))) + return NULL; + + return skb; + } + + return NULL; +} + +static inline int length_to_duration(struct taprio_sched *q, int len) +{ + return (len * q->picos_per_byte) / 1000; +} + +static struct sk_buff *taprio_dequeue(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry; + struct sk_buff *skb; + u32 gate_mask; + int i; + + rcu_read_lock(); + entry = rcu_dereference(q->current_entry); + /* if there's no entry, it means that the schedule didn't + * start yet, so force all gates to be open, this is in + * accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5 + * "AdminGateSates" + */ + gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN; + rcu_read_unlock(); + + if (!gate_mask) + return NULL; + + for (i = 0; i < dev->num_tx_queues; i++) { + struct Qdisc *child = q->qdiscs[i]; + ktime_t guard; + int prio; + int len; + u8 tc; + + if (unlikely(!child)) + continue; + + skb = child->ops->peek(child); + if (!skb) + continue; + + prio = skb->priority; + tc = netdev_get_prio_tc_map(dev, prio); + + if (!(gate_mask & BIT(tc))) + continue; + + len = qdisc_pkt_len(skb); + guard = ktime_add_ns(q->get_time(), + length_to_duration(q, len)); + + /* In the case that there's no gate entry, there's no + * guard band ... + */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + ktime_after(guard, entry->close_time)) + return NULL; + + /* ... and no budget. */ + if (gate_mask != TAPRIO_ALL_GATES_OPEN && + atomic_sub_return(len, &entry->budget) < 0) + return NULL; + + skb = child->ops->dequeue(child); + if (unlikely(!skb)) + return NULL; + + qdisc_bstats_update(sch, skb); + qdisc_qstats_backlog_dec(sch, skb); + sch->q.qlen--; + + return skb; + } + + return NULL; +} + +static bool should_restart_cycle(const struct taprio_sched *q, + const struct sched_entry *entry) +{ + WARN_ON(!entry); + + return list_is_last(&entry->list, &q->entries); +} + +static enum hrtimer_restart advance_sched(struct hrtimer *timer) +{ + struct taprio_sched *q = container_of(timer, struct taprio_sched, + advance_timer); + struct sched_entry *entry, *next; + struct Qdisc *sch = q->root; + ktime_t close_time; + + spin_lock(&q->current_entry_lock); + entry = rcu_dereference_protected(q->current_entry, + lockdep_is_held(&q->current_entry_lock)); + + /* This is the case that it's the first time that the schedule + * runs, so it only happens once per schedule. The first entry + * is pre-calculated during the schedule initialization. + */ + if (unlikely(!entry)) { + next = list_first_entry(&q->entries, struct sched_entry, + list); + close_time = next->close_time; + goto first_run; + } + + if (should_restart_cycle(q, entry)) + next = list_first_entry(&q->entries, struct sched_entry, + list); + else + next = list_next_entry(entry, list); + + close_time = ktime_add_ns(entry->close_time, next->interval); + + next->close_time = close_time; + atomic_set(&next->budget, + (next->interval * 1000) / q->picos_per_byte); + +first_run: + rcu_assign_pointer(q->current_entry, next); + spin_unlock(&q->current_entry_lock); + + hrtimer_set_expires(&q->advance_timer, close_time); + + rcu_read_lock(); + __netif_schedule(sch); + rcu_read_unlock(); + + return HRTIMER_RESTART; +} + +static const struct nla_policy entry_policy[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { + [TCA_TAPRIO_SCHED_ENTRY_INDEX] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_CMD] = { .type = NLA_U8 }, + [TCA_TAPRIO_SCHED_ENTRY_GATE_MASK] = { .type = NLA_U32 }, + [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] = { .type = NLA_U32 }, +}; + +static const struct nla_policy entry_list_policy[TCA_TAPRIO_SCHED_MAX + 1] = { + [TCA_TAPRIO_SCHED_ENTRY] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = { + [TCA_TAPRIO_ATTR_PRIOMAP] = { + .len = sizeof(struct tc_mqprio_qopt) + }, + [TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_BASE_TIME] = { .type = NLA_S64 }, + [TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] = { .type = NLA_NESTED }, + [TCA_TAPRIO_ATTR_SCHED_CLOCKID] = { .type = NLA_S32 }, +}; + +static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry, + struct netlink_ext_ack *extack) +{ + u32 interval = 0; + + if (tb[TCA_TAPRIO_SCHED_ENTRY_CMD]) + entry->command = nla_get_u8( + tb[TCA_TAPRIO_SCHED_ENTRY_CMD]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]) + entry->gate_mask = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_GATE_MASK]); + + if (tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]) + interval = nla_get_u32( + tb[TCA_TAPRIO_SCHED_ENTRY_INTERVAL]); + + if (interval == 0) { + NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry"); + return -EINVAL; + } + + entry->interval = interval; + + return 0; +} + +static int parse_sched_entry(struct nlattr *n, struct sched_entry *entry, + int index, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; + int err; + + err = nla_parse_nested(tb, TCA_TAPRIO_SCHED_ENTRY_MAX, n, + entry_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + entry->index = index; + + return fill_sched_entry(tb, entry, extack); +} + +/* Returns the number of entries in case of success */ +static int parse_sched_single_entry(struct nlattr *n, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb_entry[TCA_TAPRIO_SCHED_ENTRY_MAX + 1] = { }; + struct nlattr *tb_list[TCA_TAPRIO_SCHED_MAX + 1] = { }; + struct sched_entry *entry; + bool found = false; + u32 index; + int err; + + err = nla_parse_nested(tb_list, TCA_TAPRIO_SCHED_MAX, + n, entry_list_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + if (!tb_list[TCA_TAPRIO_SCHED_ENTRY]) { + NL_SET_ERR_MSG(extack, "Single-entry must include an entry"); + return -EINVAL; + } + + err = nla_parse_nested(tb_entry, TCA_TAPRIO_SCHED_ENTRY_MAX, + tb_list[TCA_TAPRIO_SCHED_ENTRY], + entry_policy, NULL); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Could not parse nested entry"); + return -EINVAL; + } + + if (!tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]) { + NL_SET_ERR_MSG(extack, "Entry must specify an index\n"); + return -EINVAL; + } + + index = nla_get_u32(tb_entry[TCA_TAPRIO_SCHED_ENTRY_INDEX]); + if (index >= q->num_entries) { + NL_SET_ERR_MSG(extack, "Index for single entry exceeds number of entries in schedule"); + return -EINVAL; + } + + list_for_each_entry(entry, &q->entries, list) { + if (entry->index == index) { + found = true; + break; + } + } + + if (!found) { + NL_SET_ERR_MSG(extack, "Could not find entry"); + return -ENOENT; + } + + err = fill_sched_entry(tb_entry, entry, extack); + if (err < 0) + return err; + + return q->num_entries; +} + +static int parse_sched_list(struct nlattr *list, + struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + struct nlattr *n; + int err, rem; + int i = 0; + + if (!list) + return -EINVAL; + + nla_for_each_nested(n, list, rem) { + struct sched_entry *entry; + + if (nla_type(n) != TCA_TAPRIO_SCHED_ENTRY) { + NL_SET_ERR_MSG(extack, "Attribute is not of type 'entry'"); + continue; + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + NL_SET_ERR_MSG(extack, "Not enough memory for entry"); + return -ENOMEM; + } + + err = parse_sched_entry(n, entry, i, extack); + if (err < 0) { + kfree(entry); + return err; + } + + list_add_tail(&entry->list, &q->entries); + i++; + } + + q->num_entries = i; + + return i; +} + +/* Returns the number of entries in case of success */ +static int parse_taprio_opt(struct nlattr **tb, struct taprio_sched *q, + struct netlink_ext_ack *extack) +{ + int err = 0; + int clockid; + + if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST] && + tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) + return -EINVAL; + + if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY] && q->num_entries == 0) + return -EINVAL; + + if (q->clockid == -1 && !tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) + return -EINVAL; + + if (tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]) + q->base_time = nla_get_s64( + tb[TCA_TAPRIO_ATTR_SCHED_BASE_TIME]); + + if (tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]) { + clockid = nla_get_s32(tb[TCA_TAPRIO_ATTR_SCHED_CLOCKID]); + + /* We only support static clockids and we don't allow + * for it to be modified after the first init. + */ + if (clockid < 0 || (q->clockid != -1 && q->clockid != clockid)) + return -EINVAL; + + q->clockid = clockid; + } + + if (tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST]) + err = parse_sched_list( + tb[TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST], q, extack); + else if (tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY]) + err = parse_sched_single_entry( + tb[TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY], q, extack); + + /* parse_sched_* return the number of entries in the schedule, + * a schedule with zero entries is an error. + */ + if (err == 0) { + NL_SET_ERR_MSG(extack, "The schedule should contain at least one entry"); + return -EINVAL; + } + + return err; +} + +static int taprio_parse_mqprio_opt(struct net_device *dev, + struct tc_mqprio_qopt *qopt, + struct netlink_ext_ack *extack) +{ + int i, j; + + if (!qopt) { + NL_SET_ERR_MSG(extack, "'mqprio' configuration is necessary"); + return -EINVAL; + } + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) { + NL_SET_ERR_MSG(extack, "Number of traffic classes is outside valid range"); + return -EINVAL; + } + + /* taprio imposes that traffic classes map 1:n to tx queues */ + if (qopt->num_tc > dev->num_tx_queues) { + NL_SET_ERR_MSG(extack, "Number of traffic classes is greater than number of HW queues"); + return -EINVAL; + } + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i < TC_BITMASK + 1; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) { + NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); + return -EINVAL; + } + } + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->num_tx_queues || + !qopt->count[i] || + last > dev->real_num_tx_queues) { + NL_SET_ERR_MSG(extack, "Invalid queue in traffic class to queue mapping"); + return -EINVAL; + } + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (last > qopt->offset[j]) { + NL_SET_ERR_MSG(extack, "Detected overlap in the traffic class to queue mapping"); + return -EINVAL; + } + } + } + + return 0; +} + +static ktime_t taprio_get_start_time(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sched_entry *entry; + ktime_t now, base, cycle; + s64 n; + + base = ns_to_ktime(q->base_time); + cycle = 0; + + /* Calculate the cycle_time, by summing all the intervals. + */ + list_for_each_entry(entry, &q->entries, list) + cycle = ktime_add_ns(cycle, entry->interval); + + if (!cycle) + return base; + + now = q->get_time(); + + if (ktime_after(base, now)) + return base; + + /* Schedule the start time for the beginning of the next + * cycle. + */ + n = div64_s64(ktime_sub_ns(now, base), cycle); + + return ktime_add_ns(base, (n + 1) * cycle); +} + +static void taprio_start_sched(struct Qdisc *sch, ktime_t start) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct sched_entry *first; + unsigned long flags; + + spin_lock_irqsave(&q->current_entry_lock, flags); + + first = list_first_entry(&q->entries, struct sched_entry, + list); + + first->close_time = ktime_add_ns(start, first->interval); + atomic_set(&first->budget, + (first->interval * 1000) / q->picos_per_byte); + rcu_assign_pointer(q->current_entry, NULL); + + spin_unlock_irqrestore(&q->current_entry_lock, flags); + + hrtimer_start(&q->advance_timer, start, HRTIMER_MODE_ABS); +} + +static int taprio_change(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[TCA_TAPRIO_ATTR_MAX + 1] = { }; + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt *mqprio = NULL; + struct ethtool_link_ksettings ecmd; + int i, err, size; + s64 link_speed; + ktime_t start; + + err = nla_parse_nested(tb, TCA_TAPRIO_ATTR_MAX, opt, + taprio_policy, extack); + if (err < 0) + return err; + + err = -EINVAL; + if (tb[TCA_TAPRIO_ATTR_PRIOMAP]) + mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]); + + err = taprio_parse_mqprio_opt(dev, mqprio, extack); + if (err < 0) + return err; + + /* A schedule with less than one entry is an error */ + size = parse_taprio_opt(tb, q, extack); + if (size < 0) + return size; + + hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS); + q->advance_timer.function = advance_sched; + + switch (q->clockid) { + case CLOCK_REALTIME: + q->get_time = ktime_get_real; + break; + case CLOCK_MONOTONIC: + q->get_time = ktime_get; + break; + case CLOCK_BOOTTIME: + q->get_time = ktime_get_boottime; + break; + case CLOCK_TAI: + q->get_time = ktime_get_clocktai; + break; + default: + return -ENOTSUPP; + } + + for (i = 0; i < dev->num_tx_queues; i++) { + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + + dev_queue = netdev_get_tx_queue(dev, i); + qdisc = qdisc_create_dflt(dev_queue, + &pfifo_qdisc_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1)), + extack); + if (!qdisc) + return -ENOMEM; + + if (i < dev->real_num_tx_queues) + qdisc_hash_add(qdisc, false); + + q->qdiscs[i] = qdisc; + } + + if (mqprio) { + netdev_set_num_tc(dev, mqprio->num_tc); + for (i = 0; i < mqprio->num_tc; i++) + netdev_set_tc_queue(dev, i, + mqprio->count[i], + mqprio->offset[i]); + + /* Always use supplied priority mappings */ + for (i = 0; i < TC_BITMASK + 1; i++) + netdev_set_prio_tc_map(dev, i, + mqprio->prio_tc_map[i]); + } + + if (!__ethtool_get_link_ksettings(dev, &ecmd)) + link_speed = ecmd.base.speed; + else + link_speed = SPEED_1000; + + q->picos_per_byte = div64_s64(NSEC_PER_SEC * 1000LL * 8, + link_speed * 1000 * 1000); + + start = taprio_get_start_time(sch); + if (!start) + return 0; + + taprio_start_sched(sch, start); + + return 0; +} + +static void taprio_destroy(struct Qdisc *sch) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct sched_entry *entry, *n; + unsigned int i; + + hrtimer_cancel(&q->advance_timer); + + if (q->qdiscs) { + for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++) + qdisc_put(q->qdiscs[i]); + + kfree(q->qdiscs); + } + q->qdiscs = NULL; + + netdev_set_num_tc(dev, 0); + + list_for_each_entry_safe(entry, n, &q->entries, list) { + list_del(&entry->list); + kfree(entry); + } +} + +static int taprio_init(struct Qdisc *sch, struct nlattr *opt, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + + INIT_LIST_HEAD(&q->entries); + spin_lock_init(&q->current_entry_lock); + + /* We may overwrite the configuration later */ + hrtimer_init(&q->advance_timer, CLOCK_TAI, HRTIMER_MODE_ABS); + + q->root = sch; + + /* We only support static clockids. Use an invalid value as default + * and get the valid one on taprio_change(). + */ + q->clockid = -1; + + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!netif_is_multiqueue(dev)) + return -EOPNOTSUPP; + + /* pre-allocate qdisc, attachment can't fail */ + q->qdiscs = kcalloc(dev->num_tx_queues, + sizeof(q->qdiscs[0]), + GFP_KERNEL); + + if (!q->qdiscs) + return -ENOMEM; + + if (!opt) + return -EINVAL; + + return taprio_change(sch, opt, extack); +} + +static struct netdev_queue *taprio_queue_get(struct Qdisc *sch, + unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1; + + if (ntx >= dev->num_tx_queues) + return NULL; + + return netdev_get_tx_queue(dev, ntx); +} + +static int taprio_graft(struct Qdisc *sch, unsigned long cl, + struct Qdisc *new, struct Qdisc **old, + struct netlink_ext_ack *extack) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + if (!dev_queue) + return -EINVAL; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + *old = q->qdiscs[cl - 1]; + q->qdiscs[cl - 1] = new; + + if (new) + new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; + + if (dev->flags & IFF_UP) + dev_activate(dev); + + return 0; +} + +static int dump_entry(struct sk_buff *msg, + const struct sched_entry *entry) +{ + struct nlattr *item; + + item = nla_nest_start(msg, TCA_TAPRIO_SCHED_ENTRY); + if (!item) + return -ENOSPC; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INDEX, entry->index)) + goto nla_put_failure; + + if (nla_put_u8(msg, TCA_TAPRIO_SCHED_ENTRY_CMD, entry->command)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, + entry->gate_mask)) + goto nla_put_failure; + + if (nla_put_u32(msg, TCA_TAPRIO_SCHED_ENTRY_INTERVAL, + entry->interval)) + goto nla_put_failure; + + return nla_nest_end(msg, item); + +nla_put_failure: + nla_nest_cancel(msg, item); + return -1; +} + +static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct taprio_sched *q = qdisc_priv(sch); + struct net_device *dev = qdisc_dev(sch); + struct tc_mqprio_qopt opt = { 0 }; + struct nlattr *nest, *entry_list; + struct sched_entry *entry; + unsigned int i; + + opt.num_tc = netdev_get_num_tc(dev); + memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + + for (i = 0; i < netdev_get_num_tc(dev); i++) { + opt.count[i] = dev->tc_to_txq[i].count; + opt.offset[i] = dev->tc_to_txq[i].offset; + } + + nest = nla_nest_start(skb, TCA_OPTIONS); + if (!nest) + return -ENOSPC; + + if (nla_put(skb, TCA_TAPRIO_ATTR_PRIOMAP, sizeof(opt), &opt)) + goto options_error; + + if (nla_put_s64(skb, TCA_TAPRIO_ATTR_SCHED_BASE_TIME, + q->base_time, TCA_TAPRIO_PAD)) + goto options_error; + + if (nla_put_s32(skb, TCA_TAPRIO_ATTR_SCHED_CLOCKID, q->clockid)) + goto options_error; + + entry_list = nla_nest_start(skb, TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST); + if (!entry_list) + goto options_error; + + list_for_each_entry(entry, &q->entries, list) { + if (dump_entry(skb, entry) < 0) + goto options_error; + } + + nla_nest_end(skb, entry_list); + + return nla_nest_end(skb, nest); + +options_error: + nla_nest_cancel(skb, nest); + return -1; +} + +static struct Qdisc *taprio_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + if (!dev_queue) + return NULL; + + return dev_queue->qdisc_sleeping; +} + +static unsigned long taprio_find(struct Qdisc *sch, u32 classid) +{ + unsigned int ntx = TC_H_MIN(classid); + + if (!taprio_queue_get(sch, ntx)) + return 0; + return ntx; +} + +static int taprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_handle |= TC_H_MIN(cl); + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + + return 0; +} + +static int taprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) + __releases(d->lock) + __acquires(d->lock) +{ + struct netdev_queue *dev_queue = taprio_queue_get(sch, cl); + + sch = dev_queue->qdisc_sleeping; + if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + gnet_stats_copy_queue(d, NULL, &sch->qstats, sch->q.qlen) < 0) + return -1; + return 0; +} + +static void taprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx; + + if (arg->stop) + return; + + arg->count = arg->skip; + for (ntx = arg->skip; ntx < dev->num_tx_queues; ntx++) { + if (arg->fn(sch, ntx + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static struct netdev_queue *taprio_select_queue(struct Qdisc *sch, + struct tcmsg *tcm) +{ + return taprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent)); +} + +static const struct Qdisc_class_ops taprio_class_ops = { + .graft = taprio_graft, + .leaf = taprio_leaf, + .find = taprio_find, + .walk = taprio_walk, + .dump = taprio_dump_class, + .dump_stats = taprio_dump_class_stats, + .select_queue = taprio_select_queue, +}; + +static struct Qdisc_ops taprio_qdisc_ops __read_mostly = { + .cl_ops = &taprio_class_ops, + .id = "taprio", + .priv_size = sizeof(struct taprio_sched), + .init = taprio_init, + .destroy = taprio_destroy, + .peek = taprio_peek, + .dequeue = taprio_dequeue, + .enqueue = taprio_enqueue, + .dump = taprio_dump, + .owner = THIS_MODULE, +}; + +static int __init taprio_module_init(void) +{ + return register_qdisc(&taprio_qdisc_ops); +} + +static void __exit taprio_module_exit(void) +{ + unregister_qdisc(&taprio_qdisc_ops); +} + +module_init(taprio_module_init); +module_exit(taprio_module_exit); +MODULE_LICENSE("GPL"); -- cgit v1.2.3 From 20916d4636a9b3c1bf562b305f91d126771edaf9 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Fri, 5 Oct 2018 15:51:54 -0700 Subject: mm/hugetlb: add mmap() encodings for 32MB and 512MB page sizes ARM64 architecture also supports 32MB and 512MB HugeTLB page sizes. This just adds mmap() system call argument encoding for them. Link: http://lkml.kernel.org/r/1537841300-6979-1-git-send-email-anshuman.khandual@arm.com Signed-off-by: Anshuman Khandual Acked-by: Punit Agrawal Acked-by: Mike Kravetz Cc: Michal Hocko Cc: Will Deacon Cc: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/uapi/asm-generic/hugetlb_encode.h | 2 ++ include/uapi/linux/memfd.h | 2 ++ include/uapi/linux/mman.h | 2 ++ include/uapi/linux/shm.h | 2 ++ 4 files changed, 8 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/asm-generic/hugetlb_encode.h b/include/uapi/asm-generic/hugetlb_encode.h index e4732d3c2998..b0f8e87235bd 100644 --- a/include/uapi/asm-generic/hugetlb_encode.h +++ b/include/uapi/asm-generic/hugetlb_encode.h @@ -26,7 +26,9 @@ #define HUGETLB_FLAG_ENCODE_2MB (21 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_8MB (23 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_16MB (24 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_32MB (25 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_256MB (28 << HUGETLB_FLAG_ENCODE_SHIFT) +#define HUGETLB_FLAG_ENCODE_512MB (29 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_1GB (30 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_2GB (31 << HUGETLB_FLAG_ENCODE_SHIFT) #define HUGETLB_FLAG_ENCODE_16GB (34 << HUGETLB_FLAG_ENCODE_SHIFT) diff --git a/include/uapi/linux/memfd.h b/include/uapi/linux/memfd.h index 015a4c0bbb47..7a8a26751c23 100644 --- a/include/uapi/linux/memfd.h +++ b/include/uapi/linux/memfd.h @@ -25,7 +25,9 @@ #define MFD_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB #define MFD_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB #define MFD_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MFD_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB #define MFD_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MFD_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB #define MFD_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB #define MFD_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MFD_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB diff --git a/include/uapi/linux/mman.h b/include/uapi/linux/mman.h index bfd5938fede6..d0f515d53299 100644 --- a/include/uapi/linux/mman.h +++ b/include/uapi/linux/mman.h @@ -28,7 +28,9 @@ #define MAP_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB #define MAP_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB #define MAP_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define MAP_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB #define MAP_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define MAP_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB #define MAP_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB #define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB diff --git a/include/uapi/linux/shm.h b/include/uapi/linux/shm.h index dde1344f047c..6507ad0afc81 100644 --- a/include/uapi/linux/shm.h +++ b/include/uapi/linux/shm.h @@ -65,7 +65,9 @@ struct shmid_ds { #define SHM_HUGE_2MB HUGETLB_FLAG_ENCODE_2MB #define SHM_HUGE_8MB HUGETLB_FLAG_ENCODE_8MB #define SHM_HUGE_16MB HUGETLB_FLAG_ENCODE_16MB +#define SHM_HUGE_32MB HUGETLB_FLAG_ENCODE_32MB #define SHM_HUGE_256MB HUGETLB_FLAG_ENCODE_256MB +#define SHM_HUGE_512MB HUGETLB_FLAG_ENCODE_512MB #define SHM_HUGE_1GB HUGETLB_FLAG_ENCODE_1GB #define SHM_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define SHM_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB -- cgit v1.2.3