Remove rcu_publish_content()

API phased-out. Cannot use call_rcu anyway.

Use rcu_xchg_pointer and synchronize_rcu or
rcu_xchg_pointer and call_rcu instead.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

tests: remove rcu_publish_content dependency

API phased-out.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

rculist: include correct dependencies

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-bp: use mremap

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-bp: New "bulletproof" RCU library flavor

Slower read-side/write-side, but do not require neither of:
urcu_init()
rcu_register_thread()
rcu_unregister_thread()

It is signal safe.

Specialized for the UST LTTng tracer port.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add missing system.h from make install

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-pointer: create specific objects and headers to deal with RCU pointers

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add test for rcu_assign_pointer()

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Fix rcu_assign_pointer() dynamic linking behavior

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

userspace-rcu formal model removal

For packaging. Moved to formal-model branch.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update formal model from local copy

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Remove ifndef for API_H

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add build support for ppc when $HOSTTYPE is "ppc"

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Separate arch_uatomic*.h from arch*.h

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update tests api*.h

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Align registry data on cache line size

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

define CACHE_LINE_SIZE in arch_*.h

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

compiler.h: use stddef.h for offsetof

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update .gitignore

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-qsbr: implement list_move algorithm

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu (mb/signal): fix list move implementation

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu (mb/signal): list move

Do no wait after a single thread at a time. When threads are Q.S., move them to
a separate list.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

list.h: add list_move

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu (signal): export urcu_init for early constructor initialization

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: use list instead of array for registry

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-qsbr: Add list sanity check at lib exit

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-qsbr: use linked list instead of array for registry

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu (signal/mb): move thread checks outside lock

Done on local variables, no need to lock.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu (signal/mb): use linked list instead of array for registry.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update list, rculist and hlist

- rculist : license ok
- list : fix list del

Fix rcutorture api.h implementations to use non-GPL lists.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add urcu list and list

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Cleanup headers

* atomic_ -> uatomic (to remove namespace clash with libkcompat)
* moved arch.h, compiler.h, arch_uatomic.h to
  /usr/include/urcu/

to make sure we do not pollute system headers.

Also add call_rcu() documentation to README.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add missing urcu-defer.{so,h} and urcu-defer-static.h

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Document call_rcu() usage

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add missing rcu_cmpxchg_pointer define

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add multiple reader queues to futex model

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Cleanup promela code for wakeup verif

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Remove stale file

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add multicoreverif paper ticketlock and spinlock models

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add futex wakeup spin model

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add futex support to accelerate synchronize_rcu() on UP

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: fix futex wakeup value

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Remove extra LDFLAGS from makefile

> cc: -lpthread: linker input file unused because linking not done

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add missing include compiler.h

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

rcu torture and api.h: remove duplicated atomic primitives

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

test_atomic: test for byte/short atomic support

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

ppc atomic: fix atomic_dec/inc

Only require 1 arg.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: remove dependency on linux/futex.h

> cc -fPIC -Wall -I. -O2 -g -lpthread -c -o urcu-defer.o `echo urcu-defer.c urcu-defer.h | sed 's/[^ ]*\.h//g'`
> In file included from urcu-defer.c:31:
> /usr/include/linux/futex.h:96: error: expected ‘)’ before ‘*’ token
> /usr/include/linux/futex.h:100: error: expected ‘)’ before ‘*’ token

Seems broken on ppc. Just for two defines, it's not worth depending on it.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu: Move urcu_init within ifdef

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

atomic ppc: fix missing casts and inline

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: ensure callbacks will never be enqueued forever

Even if there are no further callbacks enqueued, ensure that after a 100ms
delay, the callback queue will be dealt with.

Required proper ordering of queue vs futex.

e.g.

 The idea is to perform the "check for empty queue" between the
&defer_thread_futex decrement and the test in wait_defer. It skips the
futex call and proceed if the list is non-empty.

As I am drilling into the problem, it looks very much like an attempt to
implement efficient wait queues in userspace based on sys_futex().

/*
 * Wake-up any waiting defer thread. Called from many concurrent
 * threads.
 */
static void wake_up_defer(void)
{
        if (unlikely(atomic_read(&defer_thread_futex) == -1)) {
                atomic_set(&defer_thread_futex, 0);
                futex(&defer_thread_futex, FUTEX_WAKE, 0,
                      NULL, NULL, 0);
        }
}

/*
 * Defer thread waiting. Single thread.
 */
static void wait_defer(void)
{
        atomic_dec(&defer_thread_futex);
        smp_mb();       /* Write futex before read queue */
        if (rcu_defer_num_callbacks()) {
                smp_mb();       /* Read queue before write futex */
                /* Callbacks are queued, don't wait. */
                atomic_set(&defer_thread_futex, 0);
        } else {
                smp_rmb();      /* Read queue before read futex */
                if (atomic_read(&defer_thread_futex) == -1)
                        futex(&defer_thread_futex, FUTEX_WAIT, -1,
                              NULL, NULL, 0);
        }
}

- call_rcu():
  * queue callbacks to perform
  * smp_mb()
  * wake_up_defer()

- defer thread:
  * for (;;)
    * wait_defer()
    * sleep 100ms (wait for more callbacks to be enqueued)
    * dequeue callbacks, execute them

The goal here is that if call_rcu() enqueues a callback (even if it
races with defer thread going to sleep), there should not be a
potentially infinite delay before it gets executed. Therefore, being
blocked in sys_futex while there is a callback to execute, without any
hope to be woken up unless another callback is queued, would not meet
that design requirement. I think that checking the number of queued
callbacks within wait_defer() as I propose here should address this
situation.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Fix urcu-defer: add missing brackets.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Cleanup: remove debug code form urcu-defer.c

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Move urcu_defer_queue to urcu-defer.c

Too big to be inline.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: make call_rcu() energy efficient using futex()

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add offsetof to compiler.h

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

ppc atomic: Fix asm format.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

add rcu_cmpxchg_pointer

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

remove volatile from prototypes in atomic code

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

update ppc atomic

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

update x86 and ppc atomic ops

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add powerpc atomic operations

cmpxchg
atomic_add_return
atomic_sub_return
atomic_add
atomic_sub
atomic_inc
atomic_dec

(already had xchg)

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

update x86_64 cmpxchg

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update atomic x86_64 cmpxchg

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

makefile update

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add inc/dec x86 atomics

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

update x86 atomic, add test atomic

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

extend x86 atomic operations

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add missing files in make clean

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: remove unnecessary memory barrier

All synchronization between queue producer/consumer is performed by the write to
"head". Before this write, none of the queued data is visible from the consumer
point of view.

Therefore, just a single wmb() is required before writing to head to ensure
correct synchronization. This matches with the rmb() after reading head on the
consumer side.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: Add fast path for empty queues

defer_barrier does not need to call synchronize_rcu() when all queues are empty.
Skip the G.P. if this is the case.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-defer: cleanup debug code

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Deferral test update

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

generic urcu deferral (call_rcu())

Found out a way to encode the queues so the standard scenario is to use a single
pointer per call_rcu().

Uses more space for:
- unaligned functions pointers.
- unaligned data pointers.
- function/data value : -2L. (this is arbitrary)

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Rename liburcu-reclaim to liburcu-defer

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

urcu-reclaim cleanup

Rename "reader" to "reclaimer", because urcu-reclaim keeps track of "reclaimer"
threads (rcu writers) and has its own reclaiming thread periodically performing
the batch reclamation.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update header heading

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Add rcu-reclaim.so library

Add "automated" RCU memory reclamation.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

add static declarations

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

qsbr: Add write+read thread support to 32-bit QSBR

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

QSBR: Implement 2-phase grace period for 32-bit arch

Ensures we never run in overflow on 32-bit arch.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Permit both 32 and 64-bit builds

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Default to architecture size, add Makefile32

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update makefile to compiler for 32-bit architectures on x86_64

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Rename define

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Fix urcu.c comment

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

qsbr: use defines to clarify code.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

qsbr: portability fixes: use unsigned long for the gp counters.

unsigned wraps properly in C (modulo ULONG_MAX + 1), IOW ULONG_MAX + 2
_is_ defined and is 1.

Rewrite rcu_gp_ongoing test to work in the unsigned case:

    a - b < 0

becomes

    a - b > ULONG_MAX / 2

This test actually means a - b > 0x7f....f which is exactly what we want
to test for in the first place, but in a portable way.

Signed-off-by: Pierre Habouzit <madcoder@debian.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

qsbr: micro optimization of the gp use.

Follow-up on 1a80f3: since now `0' for a gp counter means "offline", just
be sure that the global GP counter is never zero. To achieve that, let its
first value ever be one, and increment it 2 by 2 like previously done.
Note that it internaly uses the fact that signed integers wraps (which the
previous code already assumed anyways) but this is undefined behaviour in
C. Using unsigned longs would probably be more portable.

This way, setting the cpu online, marking a quiescent state is just a
matter of copying the global gp counter instead of incrementing it by one.

This saves one CPU instruction, and supposedly even register use for
architectures providing memory to memory copy operands.

Signed-off-by: Pierre Habouzit <madcoder@debian.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

qsbr: save two full smp_mb() when the writer is also a reader.

Now that you've put the barriers before taking lock, and after releasing
it, one can expand the _rcu_thread_{on,off}line call, and optimize two
barrier calls away. (this is patch 1/2).

Signed-off-by: Pierre Habouzit <madcoder@debian.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

rename QSBR force_mb_all_threads to smp_mb

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Move mb() outside of the synchronize C.S.

Will be useful for future Q.S. merging. Does not change the RCU g.p. guarantee.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Ensure LOAD_SHARED/STORE_SHARED semantic is used in QSBR RCU

Ensures all volatile accesses are indeed volatile.
On architectures without coherent caches, will perform the proper cache flushes
when needed.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

QSBR offline thread micro-optimization

> That's an interesting paper for sure. I had one micro-optimization in
> mind when I read the paper for QSBR, you can decide that making a CPU
> offline can be done by writing 0 to the per thread counter, instead of
> reading the global counter. It saves a load from a shared variable,
> which probably helps in its tiny way.
>

In wait_for_quiescent_state, the test for Q.S. is :

                while (rcu_gp_ongoing(index->rcu_reader_qs_gp) &&
                       (*index->rcu_reader_qs_gp - urcu_gp_ctr < 0))
                        cpu_relax();

where :

static inline int rcu_gp_ongoing(long *value)
{
        if (value == NULL)
                return 0;

        return LOAD_SHARED(*value) & 1;
}

Your proposal would work for the rcu_gp_ongoing test, as it only checks
for the parity. Given this test is enough to guarantee that we skip the
reader thread, then yes, it seems to work just fine.

Proposed-by: Pierre Habouzit <madcoder@debian.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Expose nop QSBR read lock to non-GPL/LGPL programs

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Update README (again)

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

update README

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Rename CONFIG_URCU_AVOID_SIGNALS to URCU_MB, and README updates

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Revert "qsbr urcu: make it safe to call rcu_sychronize from a registered thread."

This reverts commit d1238495fdaf1c85447690231bf5d1838b83bf88.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

qsbr urcu: make it safe to call rcu_sychronize from a registered thread

Actually, the proper way to deal with threads registered as readers but also
calling synchronize_rcu() is to mark them as offline while the synchronize is in
progress.

Else, since calling rcu_sychronize will increment urcu_gp_ctr, we will be
stupidly waiting for ourselves and deadlock.

Original-patch-from: Pierre Habouzit <madcoder@debian.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>