From: "Paul E. McKenney" <paulmck@kernel.org> To: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org>, Joel Fernandes <joel@joelfernandes.org>, rcu <rcu@vger.kernel.org>, LKML <linux-kernel@vger.kernel.org>, "kernel-team@fb.com," <kernel-team@fb.com>, Ingo Molnar <mingo@kernel.org>, dipankar <dipankar@in.ibm.com>, Andrew Morton <akpm@linux-foundation.org>, Mathieu Desnoyers <mathieu.desnoyers@efficios.com>, Josh Triplett <josh@joshtriplett.org>, Thomas Glexiner <tglx@linutronix.de>, Peter Zijlstra <peterz@infradead.org>, David Howells <dhowells@redhat.com>, Eric Dumazet <edumazet@google.com>, Frederic Weisbecker <fweisbec@gmail.com>, Oleg Nesterov <oleg@redhat.com>, Masami Hiramatsu <mhiramat@kernel.org> Subject: Re: [PATCH RFC tip/core/rcu 09/16] rcu-tasks: Add an RCU-tasks rude variant Date: Sun, 10 May 2020 19:44:27 -0700 Message-ID: <20200511024427.GT2869@paulmck-ThinkPad-P72> (raw) In-Reply-To: <CAJhGHyB4xQqKpYwOZdznVTzGjLaJuDPy4upDny9mdnUb1oAKCg@mail.gmail.com> On Mon, May 11, 2020 at 08:06:29AM +0800, Lai Jiangshan wrote: > On Sun, May 10, 2020 at 11:49 PM Paul E. McKenney <paulmck@kernel.org> wrote: > > > > On Sun, May 10, 2020 at 05:59:27PM +0800, Lai Jiangshan wrote: > > > On Tue, Mar 17, 2020 at 6:03 AM Steven Rostedt <rostedt@goodmis.org> wrote: > > > > > > > > On Mon, 16 Mar 2020 17:45:40 -0400 > > > > Joel Fernandes <joel@joelfernandes.org> wrote: > > > > > > > > > > > > > > > > Same for the function side (if not even more so). This would require adding > > > > > > a srcu_read_lock() to all functions that can be traced! That would be a huge > > > > > > kill in performance. Probably to the point no one would bother even using > > > > > > function tracer. > > > > > > > > > > Point well taken! Thanks, > > > > > > > > Actually, it's worse than that. (We talked about this on IRC but I wanted > > > > it documented here too). > > > > > > > > You can't use any type of locking, unless you insert it around all the > > > > callers of the nops (which is unreasonable). > > > > > > > > That is, we have gcc -pg -mfentry that creates at the start of all traced > > > > functions: > > > > > > > > <some_func>: > > > > call __fentry__ > > > > [code for function here] > > > > > > > > At boot up (or even by the compiler itself) we convert that to: > > > > > > > > <some_func>: > > > > nop > > > > [code for function here] > > > > > > > > > > > > When we want to trace this function we use text_poke (with current kernels) > > > > and convert it to this: > > > > > > > > <some_func>: > > > > call trace_trampoline > > > > [code for function here] > > > > > > > > > > > > That trace_trampoline can be allocated, which means when its no longer > > > > needed, it must be freed. But when do we know it's safe to free it? Here's > > > > the issue. > > > > > > > > > > > > <some_func>: > > > > call trace_trampoline <- interrupt happens just after the jump > > > > [code for function here] > > > > > > > > Now the task has just executed the call to the trace_trampoline. Which > > > > means the instruction pointer is set to the start of the trampoline. But it > > > > has yet executed that trampoline. > > > > > > > > Now if the task is preempted, and a real time hog is keeping it from > > > > running for minutes at a time (which is possible!). And in the mean time, > > > > we are done with that trampoline and free it. What happens when that task > > > > is scheduled back? There's no more trampoline to execute even though its > > > > instruction pointer is to execute the first operand on the trampoline! > > > > > > > > I used the analogy of jumping off the cliff expecting a magic carpet to be > > > > there to catch you, and just before you land, it disappears. That would be > > > > a very bad day indeed! > > > > > > > > We have no way to add a grace period between the start of a function (can > > > > be *any* function) and the start of the trampoline. > > > > > > Hello > > > > > > I think adding a small number of instructions to preempt_schedule_irq() > > > is sufficient to create the needed protected region between the start > > > of a function and the trampoline body. > > > > > > preempt_schedule_irq() { > > > + if (unlikely(is_trampoline_page(page_of(interrupted_ip)))) { > > > + return; // don't do preempt schedule > > > + > > > + } > > > preempt_schedule_irq() original body > > > } > > > > > > // generated on trampoline pages > > > trace_trampoline() { > > > preempt_disable(); > > > trace_trampoline body > > > jmp preempt_enable_traced(clobbers) > > > } > > > > > > asm(kernel text): > > > preempt_enable_traced: > > > preempt_enable_notrace(); > > > restore cobblers > > > return(the return ip on the stack is traced_function_start_code) > > > > > > > > > If the number of instructions added in preempt_schedule_irq() and > > > the complexity to make trampoline ip detectable(is_trampoline_page(), > > > or is_trampoline_range()) are small, and tasks_rcu is rendered useless, > > > I think it will be win-win. > > > > It certainly would provide a nice reduction in code size! > > > > This would provide a zero-instructions preempt_disable() at the beginning > > of the trampoline and a zero-instructions preempt_enable_no_resched() at > > the end, correct? If so, wouldn't this create a potentially long (though > > "weak") preempt-disable region extending to the next preempt_enable(), > > local_bh_enable(), schedule(), interrupt, transition to userspace, > > or similar? This could be quite some time. Note that cond_resched() > > wouldn't help, given that this is only in PREEMPT=y kernels. > > > > The "weak" refers to the fact that if a second resched IPI arrived in the > > meantime, preemption would then happen. But without that second IPI, > > the request for preemption could be ignored for quite some time. > > > > Or am I missing something here? > > Hello, > > I'm sorry to note that preempt_enable_traced() is in *kernel text*, it > is *not* in trace_trampoline_protected region. So preempt_enable_traced() > can be preempted. And preempt_enable_notrace() in it checks any previous > resched requested during the trampoline. So no resched request is lost. > > The idea is that "semi-automatically preempt-disable-protecting" > the trampoline. "semi" means the trampoline still needs > preempt_disable() and the beginning, and preempt_enable() at > the end after leaving trace_trampoline_preempt_protected region. > "automatically" means the region between the start ip of > trampoline and the first preempt_disable() is also protected. > This automatically protected region is IP based, which means the > code should be put in "trace_trampoline_preempt_protected". Good point, and I did fail to connect the dots in your earlier email. > In my previous email, "trace_trampoline_preempt_protected" is detected > by information in the "struct page". But the trampolines are often > created in module_alloc() region, if so, 13-page bitmap is sufficient > to store "is this virtual-page-frame-number in trace_trampoline?" info > for all vpfn in 1520 MB module_alloc() region. If the bitmap > is too big for some cases, we might need to use bloom filter > for the fast path. I still don't know what is the best way to control > the ip of trace_trampoline or attach info to it and to fast detect it. Or perhaps use a different approach to trampoline allocation as Masami suggests. Thanx, Paul > Thanks, > Lai > > > > > Thanx, Paul > > > > > Thanks > > > > > > Lai > > > > > > > Since the problem is > > > > that the task was non-voluntarily preempted before it could execute the > > > > trampoline, and that trampolines are not allowed (suppose) to call > > > > schedule, then we have our quiescent state to track (voluntary scheduling). > > > > When all tasks have either voluntarily scheduled, or entered user space > > > > after disconnecting a trampoline from a function, we know that it is safe to > > > > free the trampoline. > > > > > > > > -- Steve
next prev parent reply index Thread overview: 171+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-03-12 18:16 [PATCH RFC tip/core/rcu 0/16] Prototype RCU usable from idle, exception, offline Paul E. McKenney 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 01/16] sched/core: Add function to sample state of non-running function paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 02/16] rcu: Add per-task state to RCU CPU stall warnings paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 03/16] rcutorture: Add flag to produce non-busy-wait task stalls paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 04/16] rcu-tasks: Move Tasks RCU to its own file paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 05/16] rcu-tasks: Create struct to hold state information paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 06/16] rcu: Reinstate synchronize_rcu_mult() paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 07/16] rcutorture: Add a test for synchronize_rcu_mult() paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 08/16] rcu-tasks: Refactor RCU-tasks to allow variants to be added paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 09/16] rcu-tasks: Add an RCU-tasks rude variant paulmck 2020-03-16 19:47 ` Joel Fernandes 2020-03-16 20:17 ` Joel Fernandes 2020-03-16 20:32 ` Paul E. McKenney 2020-03-16 21:32 ` Steven Rostedt 2020-03-16 21:45 ` Joel Fernandes 2020-03-16 22:03 ` Steven Rostedt 2020-03-16 22:11 ` Paul E. McKenney 2020-05-10 9:59 ` Lai Jiangshan 2020-05-10 15:49 ` Paul E. McKenney 2020-05-11 0:06 ` Lai Jiangshan 2020-05-11 2:44 ` Paul E. McKenney [this message] 2020-05-11 0:44 ` Masami Hiramatsu 2020-05-11 16:07 ` Steven Rostedt 2020-05-11 19:48 ` Steven Rostedt 2020-03-16 20:29 ` Paul E. McKenney 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 10/16] rcutorture: Add torture tests for RCU Tasks Rude paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 11/16] rcu-tasks: Use unique names for RCU-Tasks kthreads and messages paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 12/16] rcu-tasks: Further refactor RCU-tasks to allow adding more variants paulmck 2020-03-12 18:16 ` [PATCH RFC tip/core/rcu 13/16] rcu-tasks: Code movement to allow more Tasks RCU variants paulmck 2020-03-12 18:17 ` [PATCH RFC tip/core/rcu 14/16] rcu: Add an RCU Tasks Trace to simplify protection of tracing hooks paulmck 2020-03-12 18:17 ` [PATCH RFC tip/core/rcu 15/16] rcutorture: Add torture tests for RCU Tasks Trace paulmck 2020-03-12 18:17 ` [PATCH RFC tip/core/rcu 16/16] rcu-tasks: Add stall warnings " paulmck 2020-03-13 14:41 ` [PATCH RFC tip/core/rcu 0/16] Prototype RCU usable from idle, exception, offline Frederic Weisbecker 2020-03-13 15:42 ` Paul E. McKenney 2020-03-15 17:45 ` Mathieu Desnoyers 2020-03-15 17:59 ` Paul E. McKenney 2020-03-16 18:36 ` Steven Rostedt 2020-03-16 18:52 ` Paul E. McKenney 2020-03-16 14:45 ` Frederic Weisbecker 2020-03-16 15:39 ` Paul E. McKenney 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 0/22] " Paul E. McKenney 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 01/22] sched/core: Add function to sample state of locked-down task paulmck 2020-03-19 17:22 ` Steven Rostedt 2020-03-19 17:35 ` Paul E. McKenney 2020-03-20 2:49 ` Paul E. McKenney 2020-03-20 3:09 ` Steven Rostedt 2020-03-20 16:27 ` Paul E. McKenney 2020-03-24 0:06 ` Joel Fernandes 2020-03-24 0:15 ` Joel Fernandes 2020-03-24 16:26 ` Paul E. McKenney 2020-03-24 15:48 ` Paul E. McKenney 2020-03-24 16:52 ` Joel Fernandes 2020-03-24 17:20 ` Paul E. McKenney 2020-03-24 18:19 ` Joel Fernandes 2020-03-25 0:58 ` Paul E. McKenney 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 02/22] rcu: Add per-task state to RCU CPU stall warnings paulmck 2020-03-19 17:27 ` Steven Rostedt 2020-03-19 17:41 ` Paul E. McKenney 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 03/22] rcutorture: Add flag to produce non-busy-wait task stalls paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 04/22] rcu-tasks: Move Tasks RCU to its own file paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 05/22] rcu-tasks: Create struct to hold state information paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 06/22] rcu: Reinstate synchronize_rcu_mult() paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 07/22] rcutorture: Add a test for synchronize_rcu_mult() paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 08/22] rcu-tasks: Refactor RCU-tasks to allow variants to be added paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 09/22] rcu-tasks: Add an RCU-tasks rude variant paulmck 2020-03-19 19:04 ` Steven Rostedt 2020-03-19 23:58 ` Paul E. McKenney 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 10/22] rcutorture: Add torture tests for RCU Tasks Rude paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 11/22] rcu-tasks: Use unique names for RCU-Tasks kthreads and messages paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 12/22] rcu-tasks: Further refactor RCU-tasks to allow adding more variants paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 13/22] rcu-tasks: Code movement to allow more Tasks RCU variants paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 14/22] rcu-tasks: Add an RCU Tasks Trace to simplify protection of tracing hooks paulmck 2020-03-19 1:37 ` Joel Fernandes 2020-03-19 1:58 ` Joel Fernandes 2020-03-19 3:40 ` Paul E. McKenney 2020-03-19 19:42 ` Steven Rostedt 2020-03-20 0:28 ` Paul E. McKenney 2020-03-20 0:48 ` Steven Rostedt 2020-03-20 2:41 ` Paul E. McKenney 2020-03-28 14:06 ` Joel Fernandes 2020-03-28 15:34 ` Paul E. McKenney 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 15/22] rcutorture: Add torture tests for RCU Tasks Trace paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 16/22] rcu-tasks: Add stall warnings " paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 17/22] rcu-tasks: Move #ifdef into tasks.h paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 18/22] rcu-tasks: Add RCU tasks to rcutorture writer stall output paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 19/22] rcu-tasks: Make rcutorture writer stall output include GP state paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 20/22] rcu-tasks: Make RCU Tasks Trace make use of RCU scheduler hooks paulmck 2020-03-19 0:10 ` [PATCH RFC v2 tip/core/rcu 21/22] rcu-tasks: Add a grace-period start time for throttling and debug paulmck 2020-03-19 0:11 ` [PATCH RFC v2 tip/core/rcu 22/22] rcu-tasks: Provide boot parameter to delay IPIs until late in grace period paulmck 2020-03-19 11:31 ` [PATCH RFC v2 tip/core/rcu 0/22] Prototype RCU usable from idle, exception, offline Mathieu Desnoyers 2020-03-19 13:13 ` Paul E. McKenney [not found] ` <20200319104614.11444-1-hdanton@sina.com> 2020-03-19 12:38 ` [PATCH RFC v2 tip/core/rcu 03/22] rcutorture: Add flag to produce non-busy-wait task stalls Paul E. McKenney [not found] ` <20200319133947.12172-1-hdanton@sina.com> 2020-03-19 15:22 ` Paul E. McKenney [not found] ` <20200320040329.9840-1-hdanton@sina.com> 2020-03-20 16:11 ` Paul E. McKenney [not found] ` <20200320071228.9740-1-hdanton@sina.com> 2020-03-20 19:14 ` [PATCH RFC v2 tip/core/rcu 04/22] rcu-tasks: Move Tasks RCU to its own file Paul E. McKenney 2020-03-27 22:23 ` [PATCH RFC v3 tip/core/rcu 0/34] Prototype RCU usable from idle, exception, offline Paul E. McKenney 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 01/34] sched/core: Add function to sample state of locked-down task paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 02/34] rcu: Add per-task state to RCU CPU stall warnings paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 03/34] rcutorture: Add flag to produce non-busy-wait task stalls paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 04/34] rcu-tasks: Move Tasks RCU to its own file paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 05/34] rcu-tasks: Create struct to hold state information paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 06/34] rcu: Reinstate synchronize_rcu_mult() paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 07/34] rcutorture: Add a test for synchronize_rcu_mult() paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 08/34] rcu-tasks: Refactor RCU-tasks to allow variants to be added paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 09/34] rcu-tasks: Add an RCU-tasks rude variant paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 10/34] rcutorture: Add torture tests for RCU Tasks Rude paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 11/34] rcu-tasks: Use unique names for RCU-Tasks kthreads and messages paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 12/34] rcu-tasks: Further refactor RCU-tasks to allow adding more variants paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 13/34] rcu-tasks: Code movement to allow more Tasks RCU variants paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 14/34] rcu-tasks: Add an RCU Tasks Trace to simplify protection of tracing hooks paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 15/34] rcutorture: Add torture tests for RCU Tasks Trace paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 16/34] rcu-tasks: Add stall warnings " paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 17/34] rcu-tasks: Move #ifdef into tasks.h paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 18/34] rcu-tasks: Add RCU tasks to rcutorture writer stall output paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 19/34] rcu-tasks: Make rcutorture writer stall output include GP state paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 20/34] rcu-tasks: Make RCU Tasks Trace make use of RCU scheduler hooks paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 21/34] rcu-tasks: Add a grace-period start time for throttling and debug paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 22/34] rcu-tasks: Provide boot parameter to delay IPIs until late in grace period paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 23/34] rcu-tasks: Split ->trc_reader_need_end paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 24/34] rcu-tasks: Add grace-period and IPI counts to statistics paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 25/34] rcu-tasks: Add Kconfig option to mediate smp_mb() vs. IPI paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 26/34] rcu-tasks: Avoid IPIing userspace/idle tasks if kernel is so built paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 27/34] rcu-tasks: Allow rcu_read_unlock_trace() under scheduler locks paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 28/34] rcu-tasks: Disable CPU hotplug across RCU tasks trace scans paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 29/34] rcu-tasks: Handle the running-offline idle-task special case paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 30/34] rcu-tasks: Make RCU tasks trace also wait for idle tasks paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 31/34] rcu-tasks: Add rcu_dynticks_zero_in_eqs() effectiveness statistics paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 32/34] rcu-tasks: Add count for idle tasks on offline CPUs paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 33/34] rcutorture: Add TRACE02 scenario enabling RCU Tasks Trace IPIs paulmck 2020-03-27 22:24 ` [PATCH v3 tip/core/rcu 34/34] rcu-tasks: Add IPI failure count to statistics paulmck 2020-04-15 18:18 ` [PATCH v4 tip/core/rcu 0/38] Prototype RCU usable from idle, exception, offline Paul E. McKenney 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 01/38] rcu: Add comments marking transitions between RCU watching and not paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 02/38] rcu-tasks: Use context-switch hook for PREEMPT=y kernels paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 03/38] sched/core: Add function to sample state of locked-down task paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 04/38] rcu: Add per-task state to RCU CPU stall warnings paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 05/38] rcu-tasks: Move Tasks RCU to its own file paulmck 2020-05-10 7:42 ` Lai Jiangshan 2020-05-10 15:39 ` Paul E. McKenney 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 06/38] rcu-tasks: Create struct to hold state information paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 07/38] rcu: Reinstate synchronize_rcu_mult() paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 08/38] rcutorture: Add a test for synchronize_rcu_mult() paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 09/38] rcu-tasks: Refactor RCU-tasks to allow variants to be added paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 10/38] rcu-tasks: Add an RCU-tasks rude variant paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 11/38] rcutorture: Add torture tests for RCU Tasks Rude paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 12/38] rcu-tasks: Use unique names for RCU-Tasks kthreads and messages paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 13/38] rcu-tasks: Further refactor RCU-tasks to allow adding more variants paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 14/38] rcu-tasks: Code movement to allow more Tasks RCU variants paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 15/38] rcu-tasks: Add an RCU Tasks Trace to simplify protection of tracing hooks paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 16/38] rcutorture: Add torture tests for RCU Tasks Trace paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 17/38] rcu-tasks: Add stall warnings " paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 18/38] rcu-tasks: Move #ifdef into tasks.h paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 19/38] rcu-tasks: Add RCU tasks to rcutorture writer stall output paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 20/38] rcu-tasks: Make rcutorture writer stall output include GP state paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 21/38] rcu-tasks: Make RCU Tasks Trace make use of RCU scheduler hooks paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 22/38] rcu-tasks: Add a grace-period start time for throttling and debug paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 23/38] rcu-tasks: Provide boot parameter to delay IPIs until late in grace period paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 24/38] rcu-tasks: Split ->trc_reader_need_end paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 25/38] rcu-tasks: Add grace-period and IPI counts to statistics paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 26/38] rcu-tasks: Add Kconfig option to mediate smp_mb() vs. IPI paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 27/38] rcu-tasks: Avoid IPIing userspace/idle tasks if kernel is so built paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 28/38] rcu-tasks: Allow rcu_read_unlock_trace() under scheduler locks paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 29/38] rcu-tasks: Disable CPU hotplug across RCU tasks trace scans paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 30/38] rcu-tasks: Handle the running-offline idle-task special case paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 31/38] rcu-tasks: Make RCU tasks trace also wait for idle tasks paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 32/38] rcu-tasks: Add rcu_dynticks_zero_in_eqs() effectiveness statistics paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 33/38] rcu-tasks: Add count for idle tasks on offline CPUs paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 34/38] rcutorture: Add TRACE02 scenario enabling RCU Tasks Trace IPIs paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 35/38] rcu-tasks: Add IPI failure count to statistics paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 36/38] rcu-tasks: Allow standalone use of TASKS_{TRACE_,}RCU paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 37/38] ftrace: Use synchronize_rcu_tasks_rude() instead of ftrace_sync() paulmck 2020-04-15 18:19 ` [PATCH v4 tip/core/rcu 38/38] rcu: Don't acquire lock in NMI handler in rcu_nmi_enter_common() paulmck
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20200511024427.GT2869@paulmck-ThinkPad-P72 \ --to=paulmck@kernel.org \ --cc=akpm@linux-foundation.org \ --cc=dhowells@redhat.com \ --cc=dipankar@in.ibm.com \ --cc=edumazet@google.com \ --cc=fweisbec@gmail.com \ --cc=jiangshanlai@gmail.com \ --cc=joel@joelfernandes.org \ --cc=josh@joshtriplett.org \ --cc=kernel-team@fb.com \ --cc=linux-kernel@vger.kernel.org \ --cc=mathieu.desnoyers@efficios.com \ --cc=mhiramat@kernel.org \ --cc=mingo@kernel.org \ --cc=oleg@redhat.com \ --cc=peterz@infradead.org \ --cc=rcu@vger.kernel.org \ --cc=rostedt@goodmis.org \ --cc=tglx@linutronix.de \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: link
RCU Archive on lore.kernel.org Archives are clonable: git clone --mirror https://lore.kernel.org/rcu/0 rcu/git/0.git # If you have public-inbox 1.1+ installed, you may # initialize and index your mirror using the following commands: public-inbox-init -V2 rcu rcu/ https://lore.kernel.org/rcu \ rcu@vger.kernel.org public-inbox-index rcu Example config snippet for mirrors Newsgroup available over NNTP: nntp://nntp.lore.kernel.org/org.kernel.vger.rcu AGPL code for this site: git clone https://public-inbox.org/public-inbox.git