Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-23 04:31:50 +00:00
Code Issues Packages Projects Releases Wiki Activity
34a14c2e63
linux/net/sched/act_gate.c

647 lines
15 KiB
C
Raw Normal View History

net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
// SPDX-License-Identifier: GPL-2.0-or-later
/* Copyright 2020 NXP */
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/rtnetlink.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <net/act_api.h>
#include <net/netlink.h>
#include <net/pkt_cls.h>
#include <net/tc_act/tc_gate.h>
static unsigned int gate_net_id;
static struct tc_action_ops act_gate_ops;
static ktime_t gate_get_time(struct tcf_gate *gact)
{
ktime_t mono = ktime_get();
switch (gact->tk_offset) {
case TK_OFFS_MAX:
return mono;
default:
return ktime_mono_to_any(mono, gact->tk_offset);
}
return KTIME_MAX;
}
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
static void gate_get_start_time(struct tcf_gate *gact, ktime_t *start)
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
{
struct tcf_gate_params *param = &gact->param;
ktime_t now, base, cycle;
u64 n;
base = ns_to_ktime(param->tcfg_basetime);
now = gate_get_time(gact);
if (ktime_after(base, now)) {
*start = base;
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
return;
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
}
cycle = param->tcfg_cycletime;
n = div64_u64(ktime_sub_ns(now, base), cycle);
*start = ktime_add_ns(base, (n + 1) * cycle);
}
static void gate_start_timer(struct tcf_gate *gact, ktime_t start)
{
ktime_t expires;
expires = hrtimer_get_expires(&gact->hitimer);
if (expires == 0)
expires = KTIME_MAX;
start = min_t(ktime_t, start, expires);
hrtimer_start(&gact->hitimer, start, HRTIMER_MODE_ABS_SOFT);
}
static enum hrtimer_restart gate_timer_func(struct hrtimer *timer)
{
struct tcf_gate *gact = container_of(timer, struct tcf_gate,
hitimer);
struct tcf_gate_params *p = &gact->param;
struct tcfg_gate_entry *next;
ktime_t close_time, now;
spin_lock(&gact->tcf_lock);
next = gact->next_entry;
/* cycle start, clear pending bit, clear total octets */
gact->current_gate_status = next->gate_state ? GATE_ACT_GATE_OPEN : 0;
gact->current_entry_octets = 0;
gact->current_max_octets = next->maxoctets;
gact->current_close_time = ktime_add_ns(gact->current_close_time,
next->interval);
close_time = gact->current_close_time;
if (list_is_last(&next->list, &p->entries))
next = list_first_entry(&p->entries,
struct tcfg_gate_entry, list);
else
next = list_next_entry(next, list);
now = gate_get_time(gact);
if (ktime_after(now, close_time)) {
ktime_t cycle, base;
u64 n;
cycle = p->tcfg_cycletime;
base = ns_to_ktime(p->tcfg_basetime);
n = div64_u64(ktime_sub_ns(now, base), cycle);
close_time = ktime_add_ns(base, (n + 1) * cycle);
}
gact->next_entry = next;
hrtimer_set_expires(&gact->hitimer, close_time);
spin_unlock(&gact->tcf_lock);
return HRTIMER_RESTART;
}
static int tcf_gate_act(struct sk_buff *skb, const struct tc_action *a,
struct tcf_result *res)
{
struct tcf_gate *gact = to_gate(a);
spin_lock(&gact->tcf_lock);
tcf_lastuse_update(&gact->tcf_tm);
bstats_update(&gact->tcf_bstats, skb);
if (unlikely(gact->current_gate_status & GATE_ACT_PENDING)) {
spin_unlock(&gact->tcf_lock);
return gact->tcf_action;
}
if (!(gact->current_gate_status & GATE_ACT_GATE_OPEN))
goto drop;
if (gact->current_max_octets >= 0) {
gact->current_entry_octets += qdisc_pkt_len(skb);
if (gact->current_entry_octets > gact->current_max_octets) {
gact->tcf_qstats.overlimits++;
goto drop;
}
}
spin_unlock(&gact->tcf_lock);
return gact->tcf_action;
drop:
gact->tcf_qstats.drops++;
spin_unlock(&gact->tcf_lock);
return TC_ACT_SHOT;
}
static const struct nla_policy entry_policy[TCA_GATE_ENTRY_MAX + 1] = {
[TCA_GATE_ENTRY_INDEX] = { .type = NLA_U32 },
[TCA_GATE_ENTRY_GATE] = { .type = NLA_FLAG },
[TCA_GATE_ENTRY_INTERVAL] = { .type = NLA_U32 },
[TCA_GATE_ENTRY_IPV] = { .type = NLA_S32 },
[TCA_GATE_ENTRY_MAX_OCTETS] = { .type = NLA_S32 },
};
static const struct nla_policy gate_policy[TCA_GATE_MAX + 1] = {
netlink: consistently use NLA_POLICY_EXACT_LEN() Change places that open-code NLA_POLICY_EXACT_LEN() to use the macro instead, giving us flexibility in how we handle the details of the macro. Signed-off-by: Johannes Berg <johannes.berg@intel.com> Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-08-18 08:17:31 +00:00
[TCA_GATE_PARMS] =
NLA_POLICY_EXACT_LEN(sizeof(struct tc_gate)),
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
[TCA_GATE_PRIORITY] = { .type = NLA_S32 },
[TCA_GATE_ENTRY_LIST] = { .type = NLA_NESTED },
[TCA_GATE_BASE_TIME] = { .type = NLA_U64 },
[TCA_GATE_CYCLE_TIME] = { .type = NLA_U64 },
[TCA_GATE_CYCLE_TIME_EXT] = { .type = NLA_U64 },
[TCA_GATE_FLAGS] = { .type = NLA_U32 },
[TCA_GATE_CLOCKID] = { .type = NLA_S32 },
};
static int fill_gate_entry(struct nlattr **tb, struct tcfg_gate_entry *entry,
struct netlink_ext_ack *extack)
{
u32 interval = 0;
entry->gate_state = nla_get_flag(tb[TCA_GATE_ENTRY_GATE]);
if (tb[TCA_GATE_ENTRY_INTERVAL])
interval = nla_get_u32(tb[TCA_GATE_ENTRY_INTERVAL]);
if (interval == 0) {
NL_SET_ERR_MSG(extack, "Invalid interval for schedule entry");
return -EINVAL;
}
entry->interval = interval;
if (tb[TCA_GATE_ENTRY_IPV])
entry->ipv = nla_get_s32(tb[TCA_GATE_ENTRY_IPV]);
else
entry->ipv = -1;
if (tb[TCA_GATE_ENTRY_MAX_OCTETS])
entry->maxoctets = nla_get_s32(tb[TCA_GATE_ENTRY_MAX_OCTETS]);
else
entry->maxoctets = -1;
return 0;
}
static int parse_gate_entry(struct nlattr *n, struct tcfg_gate_entry *entry,
int index, struct netlink_ext_ack *extack)
{
struct nlattr *tb[TCA_GATE_ENTRY_MAX + 1] = { };
int err;
err = nla_parse_nested(tb, TCA_GATE_ENTRY_MAX, n, entry_policy, extack);
if (err < 0) {
NL_SET_ERR_MSG(extack, "Could not parse nested entry");
return -EINVAL;
}
entry->index = index;
return fill_gate_entry(tb, entry, extack);
}
static void release_entry_list(struct list_head *entries)
{
struct tcfg_gate_entry *entry, *e;
list_for_each_entry_safe(entry, e, entries, list) {
list_del(&entry->list);
kfree(entry);
}
}
static int parse_gate_list(struct nlattr *list_attr,
struct tcf_gate_params *sched,
struct netlink_ext_ack *extack)
{
struct tcfg_gate_entry *entry;
struct nlattr *n;
int err, rem;
int i = 0;
if (!list_attr)
return -EINVAL;
nla_for_each_nested(n, list_attr, rem) {
if (nla_type(n) != TCA_GATE_ONE_ENTRY) {
NL_SET_ERR_MSG(extack, "Attribute isn't type 'entry'");
continue;
}
entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
if (!entry) {
NL_SET_ERR_MSG(extack, "Not enough memory for entry");
err = -ENOMEM;
goto release_list;
}
err = parse_gate_entry(n, entry, i, extack);
if (err < 0) {
kfree(entry);
goto release_list;
}
list_add_tail(&entry->list, &sched->entries);
i++;
}
sched->num_entries = i;
return i;
release_list:
release_entry_list(&sched->entries);
return err;
}
net/sched: act_gate: fix configuration of the periodic timer assigning a dummy value of 'clock_id' to avoid cancellation of the cycle timer before its initialization was a temporary solution, and we still need to handle the case where act_gate timer parameters are changed by commands like the following one: # tc action replace action gate <parameters> the fix consists in the following items: 1) remove the workaround assignment of 'clock_id', and init the list of entries before the first error path after IDR atomic check/allocation 2) validate 'clock_id' earlier: there is no need to do IDR atomic check/allocation if we know that 'clock_id' is a bad value 3) use a dedicated function, 'gate_setup_timer()', to ensure that the timer is cancelled and re-initialized on action overwrite, and also ensure we initialize the timer in the error path of tcf_gate_init() v3: improve comment in the error path of tcf_gate_init() (thanks to Vladimir Oltean) v2: avoid 'goto' in gate_setup_timer (thanks to Cong Wang) CC: Ivan Vecera <ivecera@redhat.com> Fixes: a01c245438c5 ("net/sched: fix a couple of splats in the error path of tfc_gate_init()") Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:21 +00:00
static void gate_setup_timer(struct tcf_gate *gact, u64 basetime,
enum tk_offsets tko, s32 clockid,
bool do_init)
{
if (!do_init) {
if (basetime == gact->param.tcfg_basetime &&
tko == gact->tk_offset &&
clockid == gact->param.tcfg_clockid)
return;
spin_unlock_bh(&gact->tcf_lock);
hrtimer_cancel(&gact->hitimer);
spin_lock_bh(&gact->tcf_lock);
}
gact->param.tcfg_basetime = basetime;
gact->param.tcfg_clockid = clockid;
gact->tk_offset = tko;
hrtimer_init(&gact->hitimer, clockid, HRTIMER_MODE_ABS_SOFT);
gact->hitimer.function = gate_timer_func;
}
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
static int tcf_gate_init(struct net *net, struct nlattr *nla,
struct nlattr *est, struct tc_action **a,
int ovr, int bind, bool rtnl_held,
struct tcf_proto *tp, u32 flags,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, gate_net_id);
enum tk_offsets tk_offset = TK_OFFS_TAI;
struct nlattr *tb[TCA_GATE_MAX + 1];
struct tcf_chain *goto_ch = NULL;
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
u64 cycletime = 0, basetime = 0;
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
struct tcf_gate_params *p;
s32 clockid = CLOCK_TAI;
struct tcf_gate *gact;
struct tc_gate *parm;
int ret = 0, err;
u32 gflags = 0;
s32 prio = -1;
ktime_t start;
u32 index;
if (!nla)
return -EINVAL;
err = nla_parse_nested(tb, TCA_GATE_MAX, nla, gate_policy, extack);
if (err < 0)
return err;
if (!tb[TCA_GATE_PARMS])
return -EINVAL;
net/sched: act_gate: fix configuration of the periodic timer assigning a dummy value of 'clock_id' to avoid cancellation of the cycle timer before its initialization was a temporary solution, and we still need to handle the case where act_gate timer parameters are changed by commands like the following one: # tc action replace action gate <parameters> the fix consists in the following items: 1) remove the workaround assignment of 'clock_id', and init the list of entries before the first error path after IDR atomic check/allocation 2) validate 'clock_id' earlier: there is no need to do IDR atomic check/allocation if we know that 'clock_id' is a bad value 3) use a dedicated function, 'gate_setup_timer()', to ensure that the timer is cancelled and re-initialized on action overwrite, and also ensure we initialize the timer in the error path of tcf_gate_init() v3: improve comment in the error path of tcf_gate_init() (thanks to Vladimir Oltean) v2: avoid 'goto' in gate_setup_timer (thanks to Cong Wang) CC: Ivan Vecera <ivecera@redhat.com> Fixes: a01c245438c5 ("net/sched: fix a couple of splats in the error path of tfc_gate_init()") Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:21 +00:00
if (tb[TCA_GATE_CLOCKID]) {
clockid = nla_get_s32(tb[TCA_GATE_CLOCKID]);
switch (clockid) {
case CLOCK_REALTIME:
tk_offset = TK_OFFS_REAL;
break;
case CLOCK_MONOTONIC:
tk_offset = TK_OFFS_MAX;
break;
case CLOCK_BOOTTIME:
tk_offset = TK_OFFS_BOOT;
break;
case CLOCK_TAI:
tk_offset = TK_OFFS_TAI;
break;
default:
NL_SET_ERR_MSG(extack, "Invalid 'clockid'");
return -EINVAL;
}
}
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
parm = nla_data(tb[TCA_GATE_PARMS]);
index = parm->index;
err = tcf_idr_check_alloc(tn, &index, a, bind);
if (err < 0)
return err;
if (err && bind)
return 0;
if (!err) {
ret = tcf_idr_create(tn, index, est, a,
&act_gate_ops, bind, false, 0);
if (ret) {
tcf_idr_cleanup(tn, index);
return ret;
}
ret = ACT_P_CREATED;
} else if (!ovr) {
tcf_idr_release(*a, bind);
return -EEXIST;
}
if (tb[TCA_GATE_PRIORITY])
prio = nla_get_s32(tb[TCA_GATE_PRIORITY]);
if (tb[TCA_GATE_BASE_TIME])
basetime = nla_get_u64(tb[TCA_GATE_BASE_TIME]);
if (tb[TCA_GATE_FLAGS])
gflags = nla_get_u32(tb[TCA_GATE_FLAGS]);
net/sched: act_gate: fix configuration of the periodic timer assigning a dummy value of 'clock_id' to avoid cancellation of the cycle timer before its initialization was a temporary solution, and we still need to handle the case where act_gate timer parameters are changed by commands like the following one: # tc action replace action gate <parameters> the fix consists in the following items: 1) remove the workaround assignment of 'clock_id', and init the list of entries before the first error path after IDR atomic check/allocation 2) validate 'clock_id' earlier: there is no need to do IDR atomic check/allocation if we know that 'clock_id' is a bad value 3) use a dedicated function, 'gate_setup_timer()', to ensure that the timer is cancelled and re-initialized on action overwrite, and also ensure we initialize the timer in the error path of tcf_gate_init() v3: improve comment in the error path of tcf_gate_init() (thanks to Vladimir Oltean) v2: avoid 'goto' in gate_setup_timer (thanks to Cong Wang) CC: Ivan Vecera <ivecera@redhat.com> Fixes: a01c245438c5 ("net/sched: fix a couple of splats in the error path of tfc_gate_init()") Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:21 +00:00
gact = to_gate(*a);
if (ret == ACT_P_CREATED)
INIT_LIST_HEAD(&gact->param.entries);
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
if (err < 0)
goto release_idr;
spin_lock_bh(&gact->tcf_lock);
p = &gact->param;
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
if (tb[TCA_GATE_CYCLE_TIME])
cycletime = nla_get_u64(tb[TCA_GATE_CYCLE_TIME]);
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
if (tb[TCA_GATE_ENTRY_LIST]) {
err = parse_gate_list(tb[TCA_GATE_ENTRY_LIST], p, extack);
if (err < 0)
goto chain_put;
}
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
if (!cycletime) {
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
struct tcfg_gate_entry *entry;
ktime_t cycle = 0;
list_for_each_entry(entry, &p->entries, list)
cycle = ktime_add_ns(cycle, entry->interval);
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
cycletime = cycle;
if (!cycletime) {
err = -EINVAL;
goto chain_put;
}
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
}
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
p->tcfg_cycletime = cycletime;
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
if (tb[TCA_GATE_CYCLE_TIME_EXT])
p->tcfg_cycletime_ext =
nla_get_u64(tb[TCA_GATE_CYCLE_TIME_EXT]);
net/sched: act_gate: fix configuration of the periodic timer assigning a dummy value of 'clock_id' to avoid cancellation of the cycle timer before its initialization was a temporary solution, and we still need to handle the case where act_gate timer parameters are changed by commands like the following one: # tc action replace action gate <parameters> the fix consists in the following items: 1) remove the workaround assignment of 'clock_id', and init the list of entries before the first error path after IDR atomic check/allocation 2) validate 'clock_id' earlier: there is no need to do IDR atomic check/allocation if we know that 'clock_id' is a bad value 3) use a dedicated function, 'gate_setup_timer()', to ensure that the timer is cancelled and re-initialized on action overwrite, and also ensure we initialize the timer in the error path of tcf_gate_init() v3: improve comment in the error path of tcf_gate_init() (thanks to Vladimir Oltean) v2: avoid 'goto' in gate_setup_timer (thanks to Cong Wang) CC: Ivan Vecera <ivecera@redhat.com> Fixes: a01c245438c5 ("net/sched: fix a couple of splats in the error path of tfc_gate_init()") Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:21 +00:00
gate_setup_timer(gact, basetime, tk_offset, clockid,
ret == ACT_P_CREATED);
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
p->tcfg_priority = prio;
p->tcfg_flags = gflags;
net/sched: act_gate: fix NULL dereference in tcf_gate_init() it is possible to see a KASAN use-after-free, immediately followed by a NULL dereference crash, with the following command: # tc action add action gate index 3 cycle-time 100000000ns \ > cycle-time-ext 100000000ns clockid CLOCK_TAI BUG: KASAN: use-after-free in tcf_action_init_1+0x8eb/0x960 Write of size 1 at addr ffff88810a5908bc by task tc/883 CPU: 0 PID: 883 Comm: tc Not tainted 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 Call Trace: dump_stack+0x75/0xa0 print_address_description.constprop.6+0x1a/0x220 kasan_report.cold.9+0x37/0x7c tcf_action_init_1+0x8eb/0x960 tcf_action_init+0x157/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 [...] KASAN: null-ptr-deref in range [0x0000000000000070-0x0000000000000077] CPU: 0 PID: 883 Comm: tc Tainted: G B 5.7.0+ #188 Hardware name: Red Hat KVM, BIOS 1.11.1-4.module+el8.1.0+4066+0f1aadab 04/01/2014 RIP: 0010:tcf_action_fill_size+0xa3/0xf0 [....] RSP: 0018:ffff88813a48f250 EFLAGS: 00010212 RAX: dffffc0000000000 RBX: 0000000000000094 RCX: ffffffffa47c3eb6 RDX: 000000000000000e RSI: 0000000000000008 RDI: 0000000000000070 RBP: ffff88810a590800 R08: 0000000000000004 R09: ffffed1027491e03 R10: 0000000000000003 R11: ffffed1027491e03 R12: 0000000000000000 R13: 0000000000000000 R14: dffffc0000000000 R15: ffff88810a590800 FS: 00007f62cae8ce40(0000) GS:ffff888147c00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f62c9d20a10 CR3: 000000013a52a000 CR4: 0000000000340ef0 Call Trace: tcf_action_init+0x172/0x2a0 tcf_action_add+0xd9/0x2f0 tc_ctl_action+0x2a3/0x39d rtnetlink_rcv_msg+0x5f3/0x920 netlink_rcv_skb+0x120/0x380 netlink_unicast+0x439/0x630 netlink_sendmsg+0x714/0xbf0 sock_sendmsg+0xe2/0x110 ____sys_sendmsg+0x5b4/0x890 ___sys_sendmsg+0xe9/0x160 __sys_sendmsg+0xd3/0x170 do_syscall_64+0x9a/0x370 entry_SYSCALL_64_after_hwframe+0x44/0xa9 this is caused by the test on 'cycletime_ext', that is still unassigned when the action is newly created. This makes the action .init() return 0 without calling tcf_idr_insert(), hence the UAF + crash. rework the logic that prevents zero values of cycle-time, as follows: 1) 'tcfg_cycletime_ext' seems to be unused in the action software path, and it was already possible by other means to obtain non-zero cycletime and zero cycletime-ext. So, removing that test should not cause any damage. 2) while at it, we must prevent overwriting configuration data with wrong ones: use a temporary variable for 'tcfg_cycletime', and validate it preserving the original semantic (that allowed computing the cycle time as the sum of all intervals, when not specified by TCA_GATE_CYCLE_TIME). 3) remove the test on 'tcfg_cycletime', no more useful, and avoid returning -EFAULT, which did not seem an appropriate return value for a wrong netlink attribute. v3: fix uninitialized 'cycletime' (thanks to Vladimir Oltean) v2: remove useless 'return;' at the end of void gate_get_start_time() Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") CC: Ivan Vecera <ivecera@redhat.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:20 +00:00
gate_get_start_time(gact, &start);
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
gact->current_close_time = start;
gact->current_gate_status = GATE_ACT_GATE_OPEN | GATE_ACT_PENDING;
gact->next_entry = list_first_entry(&p->entries,
struct tcfg_gate_entry, list);
goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
gate_start_timer(gact, start);
spin_unlock_bh(&gact->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
return ret;
chain_put:
spin_unlock_bh(&gact->tcf_lock);
if (goto_ch)
tcf_chain_put_by_act(goto_ch);
release_idr:
net/sched: act_gate: fix configuration of the periodic timer assigning a dummy value of 'clock_id' to avoid cancellation of the cycle timer before its initialization was a temporary solution, and we still need to handle the case where act_gate timer parameters are changed by commands like the following one: # tc action replace action gate <parameters> the fix consists in the following items: 1) remove the workaround assignment of 'clock_id', and init the list of entries before the first error path after IDR atomic check/allocation 2) validate 'clock_id' earlier: there is no need to do IDR atomic check/allocation if we know that 'clock_id' is a bad value 3) use a dedicated function, 'gate_setup_timer()', to ensure that the timer is cancelled and re-initialized on action overwrite, and also ensure we initialize the timer in the error path of tcf_gate_init() v3: improve comment in the error path of tcf_gate_init() (thanks to Vladimir Oltean) v2: avoid 'goto' in gate_setup_timer (thanks to Cong Wang) CC: Ivan Vecera <ivecera@redhat.com> Fixes: a01c245438c5 ("net/sched: fix a couple of splats in the error path of tfc_gate_init()") Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:21 +00:00
/* action is not inserted in any list: it's safe to init hitimer
* without taking tcf_lock.
*/
if (ret == ACT_P_CREATED)
gate_setup_timer(gact, gact->param.tcfg_basetime,
gact->tk_offset, gact->param.tcfg_clockid,
true);
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
tcf_idr_release(*a, bind);
return err;
}
static void tcf_gate_cleanup(struct tc_action *a)
{
struct tcf_gate *gact = to_gate(a);
struct tcf_gate_params *p;
p = &gact->param;
net/sched: act_gate: fix configuration of the periodic timer assigning a dummy value of 'clock_id' to avoid cancellation of the cycle timer before its initialization was a temporary solution, and we still need to handle the case where act_gate timer parameters are changed by commands like the following one: # tc action replace action gate <parameters> the fix consists in the following items: 1) remove the workaround assignment of 'clock_id', and init the list of entries before the first error path after IDR atomic check/allocation 2) validate 'clock_id' earlier: there is no need to do IDR atomic check/allocation if we know that 'clock_id' is a bad value 3) use a dedicated function, 'gate_setup_timer()', to ensure that the timer is cancelled and re-initialized on action overwrite, and also ensure we initialize the timer in the error path of tcf_gate_init() v3: improve comment in the error path of tcf_gate_init() (thanks to Vladimir Oltean) v2: avoid 'goto' in gate_setup_timer (thanks to Cong Wang) CC: Ivan Vecera <ivecera@redhat.com> Fixes: a01c245438c5 ("net/sched: fix a couple of splats in the error path of tfc_gate_init()") Fixes: a51c328df310 ("net: qos: introduce a gate control flow action") Signed-off-by: Davide Caratti <dcaratti@redhat.com> Acked-by: Vladimir Oltean <vladimir.oltean@nxp.com> Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-16 20:25:21 +00:00
hrtimer_cancel(&gact->hitimer);
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
release_entry_list(&p->entries);
}
static int dumping_entry(struct sk_buff *skb,
struct tcfg_gate_entry *entry)
{
struct nlattr *item;
item = nla_nest_start_noflag(skb, TCA_GATE_ONE_ENTRY);
if (!item)
return -ENOSPC;
if (nla_put_u32(skb, TCA_GATE_ENTRY_INDEX, entry->index))
goto nla_put_failure;
if (entry->gate_state && nla_put_flag(skb, TCA_GATE_ENTRY_GATE))
goto nla_put_failure;
if (nla_put_u32(skb, TCA_GATE_ENTRY_INTERVAL, entry->interval))
goto nla_put_failure;
if (nla_put_s32(skb, TCA_GATE_ENTRY_MAX_OCTETS, entry->maxoctets))
goto nla_put_failure;
if (nla_put_s32(skb, TCA_GATE_ENTRY_IPV, entry->ipv))
goto nla_put_failure;
return nla_nest_end(skb, item);
nla_put_failure:
nla_nest_cancel(skb, item);
return -1;
}
static int tcf_gate_dump(struct sk_buff *skb, struct tc_action *a,
int bind, int ref)
{
unsigned char *b = skb_tail_pointer(skb);
struct tcf_gate *gact = to_gate(a);
struct tc_gate opt = {
.index = gact->tcf_index,
.refcnt = refcount_read(&gact->tcf_refcnt) - ref,
.bindcnt = atomic_read(&gact->tcf_bindcnt) - bind,
};
struct tcfg_gate_entry *entry;
struct tcf_gate_params *p;
struct nlattr *entry_list;
struct tcf_t t;
spin_lock_bh(&gact->tcf_lock);
opt.action = gact->tcf_action;
p = &gact->param;
if (nla_put(skb, TCA_GATE_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
if (nla_put_u64_64bit(skb, TCA_GATE_BASE_TIME,
p->tcfg_basetime, TCA_GATE_PAD))
goto nla_put_failure;
if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME,
p->tcfg_cycletime, TCA_GATE_PAD))
goto nla_put_failure;
if (nla_put_u64_64bit(skb, TCA_GATE_CYCLE_TIME_EXT,
p->tcfg_cycletime_ext, TCA_GATE_PAD))
goto nla_put_failure;
if (nla_put_s32(skb, TCA_GATE_CLOCKID, p->tcfg_clockid))
goto nla_put_failure;
if (nla_put_u32(skb, TCA_GATE_FLAGS, p->tcfg_flags))
goto nla_put_failure;
if (nla_put_s32(skb, TCA_GATE_PRIORITY, p->tcfg_priority))
goto nla_put_failure;
entry_list = nla_nest_start_noflag(skb, TCA_GATE_ENTRY_LIST);
if (!entry_list)
goto nla_put_failure;
list_for_each_entry(entry, &p->entries, list) {
if (dumping_entry(skb, entry) < 0)
goto nla_put_failure;
}
nla_nest_end(skb, entry_list);
tcf_tm_dump(&t, &gact->tcf_tm);
if (nla_put_64bit(skb, TCA_GATE_TM, sizeof(t), &t, TCA_GATE_PAD))
goto nla_put_failure;
spin_unlock_bh(&gact->tcf_lock);
return skb->len;
nla_put_failure:
spin_unlock_bh(&gact->tcf_lock);
nlmsg_trim(skb, b);
return -1;
}
static int tcf_gate_walker(struct net *net, struct sk_buff *skb,
struct netlink_callback *cb, int type,
const struct tc_action_ops *ops,
struct netlink_ext_ack *extack)
{
struct tc_action_net *tn = net_generic(net, gate_net_id);
return tcf_generic_walker(tn, skb, cb, type, ops, extack);
}
net: qos offload add flow status with dropped count This patch adds a drop frames counter to tc flower offloading. Reporting h/w dropped frames is necessary for some actions. Some actions like police action and the coming introduced stream gate action would produce dropped frames which is necessary for user. Status update shows how many filtered packets increasing and how many dropped in those packets. v2: Changes - Update commit comments suggest by Jiri Pirko. Signed-off-by: Po Liu <Po.Liu@nxp.com> Reviewed-by: Simon Horman <simon.horman@netronome.com> Reviewed-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-19 06:01:07 +00:00
static void tcf_gate_stats_update(struct tc_action *a, u64 bytes, u64 packets,
u64 drops, u64 lastuse, bool hw)
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
{
struct tcf_gate *gact = to_gate(a);
struct tcf_t *tm = &gact->tcf_tm;
net: qos offload add flow status with dropped count This patch adds a drop frames counter to tc flower offloading. Reporting h/w dropped frames is necessary for some actions. Some actions like police action and the coming introduced stream gate action would produce dropped frames which is necessary for user. Status update shows how many filtered packets increasing and how many dropped in those packets. v2: Changes - Update commit comments suggest by Jiri Pirko. Signed-off-by: Po Liu <Po.Liu@nxp.com> Reviewed-by: Simon Horman <simon.horman@netronome.com> Reviewed-by: Vlad Buslov <vladbu@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-06-19 06:01:07 +00:00
tcf_action_update_stats(a, bytes, packets, drops, hw);
net: qos: introduce a gate control flow action Introduce a ingress frame gate control flow action. Tc gate action does the work like this: Assume there is a gate allow specified ingress frames can be passed at specific time slot, and be dropped at specific time slot. Tc filter chooses the ingress frames, and tc gate action would specify what slot does these frames can be passed to device and what time slot would be dropped. Tc gate action would provide an entry list to tell how much time gate keep open and how much time gate keep state close. Gate action also assign a start time to tell when the entry list start. Then driver would repeat the gate entry list cyclically. For the software simulation, gate action requires the user assign a time clock type. Below is the setting example in user space. Tc filter a stream source ip address is 192.168.0.20 and gate action own two time slots. One is last 200ms gate open let frame pass another is last 100ms gate close let frames dropped. When the ingress frames have reach total frames over 8000000 bytes, the excessive frames will be dropped in that 200000000ns time slot. > tc qdisc add dev eth0 ingress > tc filter add dev eth0 parent ffff: protocol ip \ flower src_ip 192.168.0.20 \ action gate index 2 clockid CLOCK_TAI \ sched-entry open 200000000 -1 8000000 \ sched-entry close 100000000 -1 -1 > tc chain del dev eth0 ingress chain 0 "sched-entry" follow the name taprio style. Gate state is "open"/"close". Follow with period nanosecond. Then next item is internal priority value means which ingress queue should put. "-1" means wildcard. The last value optional specifies the maximum number of MSDU octets that are permitted to pass the gate during the specified time interval. Base-time is not set will be 0 as default, as result start time would be ((N + 1) * cycletime) which is the minimal of future time. Below example shows filtering a stream with destination mac address is 10:00:80:00:00:00 and ip type is ICMP, follow the action gate. The gate action would run with one close time slot which means always keep close. The time cycle is total 200000000ns. The base-time would calculate by: 1357000000000 + (N + 1) * cycletime When the total value is the future time, it will be the start time. The cycletime here would be 200000000ns for this case. > tc filter add dev eth0 parent ffff: protocol ip \ flower skip_hw ip_proto icmp dst_mac 10:00:80:00:00:00 \ action gate index 12 base-time 1357000000000 \ sched-entry close 200000000 -1 -1 \ clockid CLOCK_TAI Signed-off-by: Po Liu <Po.Liu@nxp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2020-05-01 00:53:15 +00:00
tm->lastuse = max_t(u64, tm->lastuse, lastuse);
}
static int tcf_gate_search(struct net *net, struct tc_action **a, u32 index)
{
struct tc_action_net *tn = net_generic(net, gate_net_id);
return tcf_idr_search(tn, a, index);
}
static size_t tcf_gate_get_fill_size(const struct tc_action *act)
{
return nla_total_size(sizeof(struct tc_gate));
}
static struct tc_action_ops act_gate_ops = {
.kind = "gate",
.id = TCA_ID_GATE,
.owner = THIS_MODULE,
.act = tcf_gate_act,
.dump = tcf_gate_dump,
.init = tcf_gate_init,
.cleanup = tcf_gate_cleanup,
.walk = tcf_gate_walker,
.stats_update = tcf_gate_stats_update,
.get_fill_size = tcf_gate_get_fill_size,
.lookup = tcf_gate_search,
.size = sizeof(struct tcf_gate),
};
static __net_init int gate_init_net(struct net *net)
{
struct tc_action_net *tn = net_generic(net, gate_net_id);
return tc_action_net_init(net, tn, &act_gate_ops);
}
static void __net_exit gate_exit_net(struct list_head *net_list)
{
tc_action_net_exit(net_list, gate_net_id);
}
static struct pernet_operations gate_net_ops = {
.init = gate_init_net,
.exit_batch = gate_exit_net,
.id = &gate_net_id,
.size = sizeof(struct tc_action_net),
};
static int __init gate_init_module(void)
{
return tcf_register_action(&act_gate_ops, &gate_net_ops);
}
static void __exit gate_cleanup_module(void)
{
tcf_unregister_action(&act_gate_ops, &gate_net_ops);
}
module_init(gate_init_module);
module_exit(gate_cleanup_module);
MODULE_LICENSE("GPL v2");
Reference in New Issue Copy Permalink