e786a31cce
The test implemented by some_qdisc_is_busy() is somewhat loosy for NOLOCK qdisc, as we may hit the following scenario : CPU1 CPU2 // in net_tx_action() clear_bit(__QDISC_STATE_SCHED...); // in some_qdisc_is_busy() val = (qdisc_is_running(q) || test_bit(__QDISC_STATE_SCHED, &q->state)); // here val is 0 but... qdisc_run(q) // ... CPU1 is going to run the qdisc next As a conseguence qdisc_run() in net_tx_action() can race with qdisc_reset() in dev_qdisc_reset(). Such race is not possible for !NOLOCK qdisc as both the above bit operations are under the root qdisc lock(). After commit021a17ed79
("pfifo_fast: drop unneeded additional lock on dequeue") the race can cause use after free and/or null ptr dereference, but the root cause is likely older. This patch addresses the issue explicitly checking for deactivation under the seqlock for NOLOCK qdisc, so that the qdisc_run() in the critical scenario becomes a no-op. Note that the enqueue() op can still execute concurrently with dev_qdisc_reset(), but that is safe due to the skb_array() locking, and we can't avoid that for NOLOCK qdiscs. Fixes:021a17ed79
("pfifo_fast: drop unneeded additional lock on dequeue") Reported-by: Li Shuang <shuali@redhat.com> Reported-and-tested-by: Davide Caratti <dcaratti@redhat.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> (Backported from commit d518d2ed8640c1cbbbb6f63939e3e65471817367). Git-Commit: d518d2ed8640c1cbbbb6f63939e3e65471817367 Git-repo: https://android.googlesource.com/kernel/common/ Change-Id: Id4e048bd00ea0d9be49f98958e648c74af965e12 Signed-off-by: Chinmay Agarwal <chinagar@codeaurora.org>
160 lines
4.2 KiB
C
160 lines
4.2 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_ns(struct qdisc_watchdog *wd, u64 expires);
|
|
|
|
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_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);
|
|
}
|
|
}
|
|
|
|
extern int tc_qdisc_flow_control(struct net_device *dev, u32 tcm_handle,
|
|
int flow_enable);
|
|
/* 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;
|
|
};
|
|
|
|
#endif
|