#undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include #include #include DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @expires: the timers expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long expires, unsigned int flags), TP_ARGS(timer, expires, flags), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = expires; __entry->now = jiffies; __entry->flags = flags; ), TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] flags=0x%08x", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->flags) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; ), TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * hrtimer_init - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_init, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, __entry->clockid == CLOCK_REALTIME ? "CLOCK_REALTIME" : "CLOCK_MONOTONIC", __entry->mode == HRTIMER_MODE_ABS ? "HRTIMER_MODE_ABS" : "HRTIMER_MODE_REL") ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = hrtimer->function; __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); ), TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = hrtimer->function; ), TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerval *const value, cputime_t expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( cputime_t, expires ) __field( long, value_sec ) __field( long, value_usec ) __field( long, interval_sec ) __field( long, interval_usec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_usec = value->it_value.tv_usec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_usec = value->it_interval.tv_usec; ), TP_printk("which=%d expires=%llu it_value=%ld.%ld it_interval=%ld.%ld", __entry->which, (unsigned long long)__entry->expires, __entry->value_sec, __entry->value_usec, __entry->interval_sec, __entry->interval_usec) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, cputime_t now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( cputime_t, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, (unsigned long long)__entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name_end(CLOCK_UNSTABLE) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include as needed. We can't follow this model because we want to take the zone id from an sreg at rule eval time so we could e.g. fill in the zone id from the packets vlan id or a e.g. nftables key : value maps. To avoid cost of per packet alloc/free of the template, use a percpu template 'scratch' object and use the refcount to detect the (unlikely) case where the template is still attached to another skb (i.e., previous skb was nfqueued ...). Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nft_ct: prepare for key-dependent error unwindFlorian Westphal1-14/+15 Next patch will add ZONE_ID set support which will need similar error unwind (put operation) as conntrack labels. Prepare for this: remove the 'label_got' boolean in favor of a switch statement that can be extended in next patch. As we already have that in the set_destroy function place that in a separate function and call it from the set init function. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nft_ct: add zone id get supportFlorian Westphal2-3/+21 Just like with counters the direction attribute is optional. We set priv->dir to MAX unconditionally to avoid duplicating the assignment for all keys with optional direction. For keys where direction is mandatory, existing code already returns an error. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nf_tables: add bitmap set typePablo Neira Ayuso3-0/+321 This patch adds a new bitmap set type. This bitmap uses two bits to represent one element. These two bits determine the element state in the current and the future generation that fits into the nf_tables commit protocol. When dumping elements back to userspace, the two bits are expanded into a struct nft_set_ext object. If no NFTA_SET_DESC_SIZE is specified, the existing automatic set backend selection prefers bitmap over hash in case of keys whose size is <= 16 bit. If the set size is know, the bitmap set type is selected if with 16 bit kets and more than 390 elements in the set, otherwise the hash table set implementation is used. For 8 bit keys, the bitmap consumes 66 bytes. For 16 bit keys, the bitmap takes 16388 bytes. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nf_tables: add space notation to setsPablo Neira Ayuso4-5/+21 The space notation allows us to classify the set backend implementation based on the amount of required memory. This provides an order of the set representation scalability in terms of memory. The size field is still left in place so use this if the userspace provides no explicit number of elements, so we cannot calculate the real memory that this set needs. This also helps us break ties in the set backend selection routine, eg. two backend implementations provide the same performance. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nf_tables: rename struct nft_set_estimate class fieldPablo Neira Ayuso4-10/+10 Use lookup as field name instead, to prepare the introduction of the memory class in a follow up patch. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nf_tables: add flush field to struct nft_set_iterPablo Neira Ayuso2-0/+5 This provides context to walk callback iterator, thus, we know if the walk happens from the set flush path. This is required by the new bitmap set type coming in a follow up patch which has no real struct nft_set_ext, so it has to allocate it based on the two bit compact element representation. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nf_tables: rename deactivate_one() to flush()Pablo Neira Ayuso4-13/+13 Although semantics are similar to deactivate() with no implicit element lookup, this is only called from the set flush path, so better rename this to flush(). Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nf_tables: use struct nft_set_iter in set element flushPablo Neira Ayuso1-7/+5 Instead of struct nft_set_dump_args, remove unnecessary wrapper structure. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nf_tables: pass netns to set->ops->remove()Pablo Neira Ayuso4-6/+9 This new parameter is required by the new bitmap set type that comes in a follow up patch. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-08netfilter: nft_exthdr: Add support for existence checkPhil Sutter2-2/+26 If NFT_EXTHDR_F_PRESENT is set, exthdr will not copy any header field data into *dest, but instead set it to 1 if the header is found and 0 otherwise. Signed-off-by: Phil Sutter <phil@nwl.cc> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> 2017-02-03net: skb_needs_check() accepts CHECKSUM_NONE for txEric Dumazet1-3/+4 My recent change missed fact that UFO would perform a complete UDP checksum before segmenting in frags. In this case skb->ip_summed is set to CHECKSUM_NONE. We need to add this valid case to skb_needs_check() Fixes: b2504a5dbef3 ("net: reduce skb_warn_bad_offload() noise") Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net: remove support for per driver ndo_busy_poll()Eric Dumazet4-21/+0 We added generic support for busy polling in NAPI layer in linux-4.5 No network driver uses ndo_busy_poll() anymore, we can get rid of the pointer in struct net_device_ops, and its use in sk_busy_loop() Saves NETIF_F_BUSY_POLL features bit. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03enic: Remove local ndo_busy_poll() implementation.David S. Miller