| /Linux-v5.10/include/trace/events/ |
| D | irq.h | 103 DECLARE_EVENT_CLASS(softirq,
128 DEFINE_EVENT(softirq, softirq_entry,
142 DEFINE_EVENT(softirq, softirq_exit,
156 DEFINE_EVENT(softirq, softirq_raise,
|
| /Linux-v5.10/fs/proc/ |
| D | stat.c | 110 u64 user, nice, system, idle, iowait, irq, softirq, steal; in show_stat() local
118 irq = softirq = steal = 0; in show_stat()
134 softirq += cpustat[CPUTIME_SOFTIRQ]; in show_stat()
156 seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq)); in show_stat()
175 softirq = cpustat[CPUTIME_SOFTIRQ]; in show_stat()
186 seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq)); in show_stat()
|
| /Linux-v5.10/arch/s390/kernel/ |
| D | vtime.c | 127 u64 timer, clock, user, guest, system, hardirq, softirq; in do_account_vtime() local
162 softirq = update_tsk_timer(&tsk->thread.softirq_timer, in do_account_vtime()
165 clock - user - guest - system - hardirq - softirq; in do_account_vtime()
182 if (softirq) in do_account_vtime()
183 account_system_index_scaled(tsk, softirq, CPUTIME_SOFTIRQ); in do_account_vtime()
185 return virt_timer_forward(user + guest + system + hardirq + softirq); in do_account_vtime()
|
| /Linux-v5.10/Documentation/RCU/ |
| D | UP.rst | 15 Example 1: softirq Suicide
20 this same list in softirq context. Suppose that the process-context scan
21 is referencing element B when it is interrupted by softirq processing,
26 from softirq, the list scan would find itself referencing a newly freed
125 then, since RCU callbacks can be invoked from softirq context,
126 the callback might be called from a softirq that interrupted
|
| D | stallwarn.rst | 57 is running at a higher priority than the RCU softirq threads.
73 prevent RCU's kthreads and softirq handlers from running.
194 2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0
195 16-...: (0 ticks this GP) idle=81c/0/0 softirq=764/764 fqs=0
219 The "softirq=" portion of the message tracks the number of RCU softirq
227 across repeated stall-warning messages, it is possible that RCU's softirq
230 kernels, if a high-priority process is starving RCU's softirq handler.
246 …0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 softirq=82/543 last_accelerate: a345/d342 dyn…
|
| D | checklist.rst | 190 be called from softirq context. In particular, it cannot block.
234 disabled, for example, in irq or softirq context. Commenting
324 with softirq disabled, e.g., via spin_lock_irqsave(),
325 spin_lock_bh(), etc. Failing to disable softirq on a given
327 the RCU softirq handler happens to run your RCU callback while
|
| /Linux-v5.10/Documentation/translations/it_IT/kernel-hacking/ |
| D | locking.rst | 178 Sincronizzazione fra il contesto utente e i softirq
181 Se un softirq condivide dati col contesto utente, avete due problemi.
182 Primo, il contesto utente corrente potrebbe essere interroto da un softirq,
185 (``include/linux/spinlock.h``) viene utilizzato. Questo disabilita i softirq
197 (``include/linux/interrupt.h``), la quale impedisce ai softirq d'essere
203 Questo caso è uguale al precedente, un tasklet viene eseguito da un softirq.
209 softirq.
234 Sincronizzazione fra softirq
237 Spesso un softirq potrebbe condividere dati con se stesso o un tasklet/timer.
239 Lo stesso softirq argument
[all …]
|
| D | hacking.rst | 40 - non associata ad alcun processo, servendo un softirq o tasklet;
50 softirq è in esecuzione su d'una CPU, nessun altro softirq può avvicendarsi
77 Attenzione che se avete la prelazione o i softirq disabilitati (vedere
101 Contesto d'interruzione software: softirq e tasklet
107 eseguita (``kernel/softirq.c``).
116 Il file ``include/linux/interrupt.h`` elenca i differenti tipi di 'softirq'.
117 Un tipo di softirq molto importante è il timer (``include/linux/timer.h``):
121 Dato che i softirq possono essere eseguiti simultaneamente su più di un
135 Potete determinate se siete in un softirq (o tasklet) utilizzando la
433 Lo scopo è di prevenire l'esecuzione di softirq e tasklet sul processore
|
| /Linux-v5.10/Documentation/locking/ |
| D | lockdep-design.rst | 55 - softirq
88 ||| \-> softirq disabled and not in softirq context
89 || \--> acquired in softirq context
120 A softirq-unsafe lock-class is automatically hardirq-unsafe as well. The
125 <softirq-safe> or <softirq-unsafe>
160 <softirq-safe> -> <softirq-unsafe>
164 thus could result in a lock inversion deadlock. Likewise, a softirq-safe
165 lock could be taken by an softirq context, interrupting a softirq-unsafe
178 - if a new softirq-safe lock is discovered, we check whether it took
179 any softirq-unsafe lock in the past.
[all …]
|
| D | seqlock.rst | 49 softirq contexts, interrupts or bottom halves must also be respectively
168 If the read side section can be invoked from hardirq or softirq context,
|
| /Linux-v5.10/Documentation/kernel-hacking/ |
| D | locking.rst | 170 If a softirq shares data with user context, you have two problems.
171 Firstly, the current user context can be interrupted by a softirq, and
186 (``include/linux/interrupt.h``), which protects you from the softirq
193 from a softirq.
199 from a softirq. From a locking point of view, tasklets and timers are
227 Often a softirq might want to share data with itself or a tasklet/timer.
232 The same softirq can run on the other CPUs: you can use a per-CPU array
234 going so far as to use a softirq, you probably care about scalable
245 tasklet, different softirq or the same or another softirq: any of them
251 Hardware interrupts usually communicate with a tasklet or softirq.
[all …]
|
| D | hacking.rst | 32 - not associated with any process, serving a softirq or tasklet;
40 by the ones above it. For example, while a softirq is running on a CPU,
41 no other softirq will preempt it, but a hardware interrupt can. However,
92 pending (usually by hardware interrupts) are run (``kernel/softirq.c``).
101 important softirq is the timer softirq (``include/linux/timer.h``): you
105 Softirqs are often a pain to deal with, since the same softirq will run
118 You can tell you are in a softirq (or tasklet) using the
|
| /Linux-v5.10/Documentation/timers/ |
| D | highres.rst | 176 red-black tree to a separate double linked list and invokes the softirq
183 context to the softirq and to the task which is woken up by the expired
199 The softirq for running the hrtimer queues and executing the callbacks has been
200 separated from the tick bound timer softirq to allow accurate delivery of high
202 timers. The execution of this softirq can still be delayed by other softirqs,
|
| /Linux-v5.10/Documentation/scheduler/ |
| D | sched-domains.rst | 35 through scheduler_tick(). It raises a softirq after the next regularly scheduled
38 in softirq context (SCHED_SOFTIRQ).
|
| /Linux-v5.10/Documentation/vm/ |
| D | page_frags.rst | 34 only usable within the softirq context.
|
| /Linux-v5.10/Documentation/core-api/irq/ |
| D | irqflags-tracing.rst | 7 The "irq-flags tracing" feature "traces" hardirq and softirq state, in
|
| /Linux-v5.10/Documentation/trace/ |
| D | ftrace.rst | 854 # | / _---=> hardirq/softirq
907 # || / _---=> hardirq/softirq
965 hardirq/softirq:
968 - 'H' - hard irq occurred inside a softirq.
1373 # || / _---=> hardirq/softirq
1424 # || / _---=> hardirq/softirq
1501 # | / _---=> hardirq/softirq
1572 # || / _---=> hardirq/softirq
1610 # || / _---=> hardirq/softirq
1724 # || / _---=> hardirq/softirq
[all …]
|
| /Linux-v5.10/Documentation/admin-guide/sysctl/ |
| D | net.rst | 139 of the driver for the per softirq cycle netdev_budget. This parameter influences
141 processing during RX softirq cycles. It is further meant for making current
151 Scales the maximum number of packets that can be processed during a TX softirq cycle.
153 net stack processing needs. Be careful to avoid making TX softirq processing a CPU hog.
|
| /Linux-v5.10/kernel/trace/ |
| D | trace_output.c | 446 int softirq; in trace_print_lat_fmt() local
451 softirq = entry->flags & TRACE_FLAG_SOFTIRQ; in trace_print_lat_fmt()
477 (hardirq && softirq) ? 'H' : in trace_print_lat_fmt()
479 softirq ? 's' : in trace_print_lat_fmt()
|
| /Linux-v5.10/kernel/ |
| D | Makefile | 7 cpu.o exit.o softirq.o resource.o \
|
| /Linux-v5.10/Documentation/networking/ |
| D | page_pool.rst | 63 This lockless guarantee naturally comes from running under a NAPI softirq.
|
| D | netdevices.rst | 110 softirq
|
| D | ppp_generic.rst | 222 from process context, not interrupt or softirq/BH context.
224 * The remaining generic layer functions may be called at softirq/BH
228 softirq/BH level but will not call it at interrupt level. Thus the
|
| /Linux-v5.10/Documentation/infiniband/ |
| D | core_locking.rst | 95 may be process context, softirq context, or interrupt context.
|
| /Linux-v5.10/Documentation/core-api/ |
| D | xarray.rst | 246 the array. It is safe to read the XArray from interrupt or softirq
250 context and then erase them in softirq context, you can do that this way::
269 /* foo_erase() is only called from softirq context */
278 If you are going to modify the XArray from interrupt or softirq context,
|
