mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-23 11:04:44 +08:00
d7bf2ebebc
There are a couple of places in net/sched/ that check skb->protocol and act
on the value there. However, in the presence of VLAN tags, the value stored
in skb->protocol can be inconsistent based on whether VLAN acceleration is
enabled. The commit quoted in the Fixes tag below fixed the users of
skb->protocol to use a helper that will always see the VLAN ethertype.
However, most of the callers don't actually handle the VLAN ethertype, but
expect to find the IP header type in the protocol field. This means that
things like changing the ECN field, or parsing diffserv values, stops
working if there's a VLAN tag, or if there are multiple nested VLAN
tags (QinQ).
To fix this, change the helper to take an argument that indicates whether
the caller wants to skip the VLAN tags or not. When skipping VLAN tags, we
make sure to skip all of them, so behaviour is consistent even in QinQ
mode.
To make the helper usable from the ECN code, move it to if_vlan.h instead
of pkt_sched.h.
v3:
- Remove empty lines
- Move vlan variable definitions inside loop in skb_protocol()
- Also use skb_protocol() helper in IP{,6}_ECN_decapsulate() and
bpf_skb_ecn_set_ce()
v2:
- Use eth_type_vlan() helper in skb_protocol()
- Also fix code that reads skb->protocol directly
- Change a couple of 'if/else if' statements to switch constructs to avoid
calling the helper twice
Reported-by: Ilya Ponetayev <i.ponetaev@ndmsystems.com>
Fixes: d8b9605d26
("net: sched: fix skb->protocol use in case of accelerated vlan path")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
190 lines
4.9 KiB
C
190 lines
4.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef __NET_PKT_SCHED_H
|
|
#define __NET_PKT_SCHED_H
|
|
|
|
#include <linux/jiffies.h>
|
|
#include <linux/ktime.h>
|
|
#include <linux/if_vlan.h>
|
|
#include <linux/netdevice.h>
|
|
#include <net/sch_generic.h>
|
|
#include <net/net_namespace.h>
|
|
#include <uapi/linux/pkt_sched.h>
|
|
|
|
#define DEFAULT_TX_QUEUE_LEN 1000
|
|
|
|
struct qdisc_walker {
|
|
int stop;
|
|
int skip;
|
|
int count;
|
|
int (*fn)(struct Qdisc *, unsigned long cl, struct qdisc_walker *);
|
|
};
|
|
|
|
#define QDISC_ALIGNTO 64
|
|
#define QDISC_ALIGN(len) (((len) + QDISC_ALIGNTO-1) & ~(QDISC_ALIGNTO-1))
|
|
|
|
static inline void *qdisc_priv(struct Qdisc *q)
|
|
{
|
|
return (char *) q + QDISC_ALIGN(sizeof(struct Qdisc));
|
|
}
|
|
|
|
/*
|
|
Timer resolution MUST BE < 10% of min_schedulable_packet_size/bandwidth
|
|
|
|
Normal IP packet size ~ 512byte, hence:
|
|
|
|
0.5Kbyte/1Mbyte/sec = 0.5msec, so that we need 50usec timer for
|
|
10Mbit ethernet.
|
|
|
|
10msec resolution -> <50Kbit/sec.
|
|
|
|
The result: [34]86 is not good choice for QoS router :-(
|
|
|
|
The things are not so bad, because we may use artificial
|
|
clock evaluated by integration of network data flow
|
|
in the most critical places.
|
|
*/
|
|
|
|
typedef u64 psched_time_t;
|
|
typedef long psched_tdiff_t;
|
|
|
|
/* Avoid doing 64 bit divide */
|
|
#define PSCHED_SHIFT 6
|
|
#define PSCHED_TICKS2NS(x) ((s64)(x) << PSCHED_SHIFT)
|
|
#define PSCHED_NS2TICKS(x) ((x) >> PSCHED_SHIFT)
|
|
|
|
#define PSCHED_TICKS_PER_SEC PSCHED_NS2TICKS(NSEC_PER_SEC)
|
|
#define PSCHED_PASTPERFECT 0
|
|
|
|
static inline psched_time_t psched_get_time(void)
|
|
{
|
|
return PSCHED_NS2TICKS(ktime_get_ns());
|
|
}
|
|
|
|
static inline psched_tdiff_t
|
|
psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound)
|
|
{
|
|
return min(tv1 - tv2, bound);
|
|
}
|
|
|
|
struct qdisc_watchdog {
|
|
u64 last_expires;
|
|
struct hrtimer timer;
|
|
struct Qdisc *qdisc;
|
|
};
|
|
|
|
void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
|
|
clockid_t clockid);
|
|
void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
|
|
|
|
void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires,
|
|
u64 delta_ns);
|
|
|
|
static inline void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd,
|
|
u64 expires)
|
|
{
|
|
return qdisc_watchdog_schedule_range_ns(wd, expires, 0ULL);
|
|
}
|
|
|
|
static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd,
|
|
psched_time_t expires)
|
|
{
|
|
qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires));
|
|
}
|
|
|
|
void qdisc_watchdog_cancel(struct qdisc_watchdog *wd);
|
|
|
|
extern struct Qdisc_ops pfifo_qdisc_ops;
|
|
extern struct Qdisc_ops bfifo_qdisc_ops;
|
|
extern struct Qdisc_ops pfifo_head_drop_qdisc_ops;
|
|
|
|
int fifo_set_limit(struct Qdisc *q, unsigned int limit);
|
|
struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops,
|
|
unsigned int limit,
|
|
struct netlink_ext_ack *extack);
|
|
|
|
int register_qdisc(struct Qdisc_ops *qops);
|
|
int unregister_qdisc(struct Qdisc_ops *qops);
|
|
void qdisc_get_default(char *id, size_t len);
|
|
int qdisc_set_default(const char *id);
|
|
|
|
void qdisc_hash_add(struct Qdisc *q, bool invisible);
|
|
void qdisc_hash_del(struct Qdisc *q);
|
|
struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
|
|
struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle);
|
|
struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
|
|
struct nlattr *tab,
|
|
struct netlink_ext_ack *extack);
|
|
void qdisc_put_rtab(struct qdisc_rate_table *tab);
|
|
void qdisc_put_stab(struct qdisc_size_table *tab);
|
|
void qdisc_warn_nonwc(const char *txt, struct Qdisc *qdisc);
|
|
bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
|
|
struct net_device *dev, struct netdev_queue *txq,
|
|
spinlock_t *root_lock, bool validate);
|
|
|
|
void __qdisc_run(struct Qdisc *q);
|
|
|
|
static inline void qdisc_run(struct Qdisc *q)
|
|
{
|
|
if (qdisc_run_begin(q)) {
|
|
/* NOLOCK qdisc must check 'state' under the qdisc seqlock
|
|
* to avoid racing with dev_qdisc_reset()
|
|
*/
|
|
if (!(q->flags & TCQ_F_NOLOCK) ||
|
|
likely(!test_bit(__QDISC_STATE_DEACTIVATED, &q->state)))
|
|
__qdisc_run(q);
|
|
qdisc_run_end(q);
|
|
}
|
|
}
|
|
|
|
/* Calculate maximal size of packet seen by hard_start_xmit
|
|
routine of this device.
|
|
*/
|
|
static inline unsigned int psched_mtu(const struct net_device *dev)
|
|
{
|
|
return dev->mtu + dev->hard_header_len;
|
|
}
|
|
|
|
static inline struct net *qdisc_net(struct Qdisc *q)
|
|
{
|
|
return dev_net(q->dev_queue->dev);
|
|
}
|
|
|
|
struct tc_cbs_qopt_offload {
|
|
u8 enable;
|
|
s32 queue;
|
|
s32 hicredit;
|
|
s32 locredit;
|
|
s32 idleslope;
|
|
s32 sendslope;
|
|
};
|
|
|
|
struct tc_etf_qopt_offload {
|
|
u8 enable;
|
|
s32 queue;
|
|
};
|
|
|
|
struct tc_taprio_sched_entry {
|
|
u8 command; /* TC_TAPRIO_CMD_* */
|
|
|
|
/* The gate_mask in the offloading side refers to traffic classes */
|
|
u32 gate_mask;
|
|
u32 interval;
|
|
};
|
|
|
|
struct tc_taprio_qopt_offload {
|
|
u8 enable;
|
|
ktime_t base_time;
|
|
u64 cycle_time;
|
|
u64 cycle_time_extension;
|
|
|
|
size_t num_entries;
|
|
struct tc_taprio_sched_entry entries[];
|
|
};
|
|
|
|
/* Reference counting */
|
|
struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload
|
|
*offload);
|
|
void taprio_offload_free(struct tc_taprio_qopt_offload *offload);
|
|
|
|
#endif
|