Comparing an offset from an object with NULL is undefined behavior
and the compiler may assume that this is never true.
This is indeed what is observed with gcc-10 miscompiling
cds_hlist_for_each_entry_rcu_2().
Fix this by introducing cds_hlist_entry_safe() rather than open-coding
the NULL check comparisons, and move cds_hlist_for_each_entry_2()
and cds_hlist_for_each_entry_safe_2() to this scheme as well.
Fix: use __atomic_load() rather than atomic load explicit
Use __atomic_load (gcc extension) rather than atomic load explict
(C11/C++11) for rcu_dereference because it does not require the input
type to be _Atomic. This fixes a regression with clang introduced by
commit 380f4b19052 ("Fix: use atomic load memory_order_consume for
rcu_dereference on C11/C++11").
Note that the cmm_smp_read_barrier_depends is removed when using
__ATOMIC_CONSUME because their memory ordering effect is redundant.
Michael Jeanson [Tue, 13 Apr 2021 20:19:06 +0000 (16:19 -0400)]
fix: HAVE_SCHED_SETAFFINITY is not defined
Use '#ifdef' instead of '#if' to test if HAVE_SCHED_SETAFFINITY is
defined. Both work but using '#if' on an undefined macro will generate a
warning with '-Wundef'.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Change-Id: Ib8e13defb79e271da880196fd0a7f7f642999048
Michael Jeanson [Thu, 1 Apr 2021 18:39:01 +0000 (14:39 -0400)]
cleanup: explicitly mark unused parameters (-Wunused-parameter)
Add the 'unused' attribute to function parameters that are unused to
allow turning on -Wunused-parameter and distinguish unused parameters
that are actual errors.
Change-Id: Ie585e37f9d38718543a31aee2e7ab3428cdfd0a5 Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Mon, 25 Jan 2021 18:36:24 +0000 (13:36 -0500)]
fix: exclude clang from GCC version blacklists
URCU_GCC_VERSION is used to blacklist specific GCC versions with known
bugs, clang also defines these macros to an equivalent GCC version it
claims to support, so exclude it.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Change-Id: Idf0980fddca6533313a3367601ddda8d8e13bfdf
The newly-released autoconf 2.70 introduces a number of breaking
changes [1] and is being rolled-out by some distros.
Amongst those changes, the AC_PROG_CC_STDC macro is marked as obsolete
and was merged into AC_PROG_CC, which we already use. On 2.70, this
results in a warning which we handle as an error.
A version check is added to invoke the AC_PROG_CC_STDC macro only when
running a pre-2.70 version of autoconf, fixing the issue.
Also, the AX_PTHREAD macro makes use of the $as_echo built-in shell
variable which no longer exists in 2.70. A patch was submitted to the
GNU Autoconf archive in March, but there have been no signs of life
given since then [2].
As such, our local copy is updated to the latest version and the patch
(which looks fairly straight-forward / safe) is applied. This should
minimize changes once we go back to an "official" version of the macro.
Michael Jeanson [Wed, 9 Dec 2020 17:05:31 +0000 (12:05 -0500)]
fix: bump tests thread limit to 4096
Machines with more than 128 CPUs are becomming more common. A
future-proof fix here would be to dynamically allocate the array, but in
the meantime bump the limit to 4096 to fix the problem on a 160 CPUs
ppc64el system where this was reported.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Cc: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Change-Id: Ib3cb5d8cb4515e6f626be33c2685fa38cb081782
Michael Jeanson [Fri, 30 Oct 2020 19:39:56 +0000 (15:39 -0400)]
fix: add -lurcu-common to pkg-config libs for each flavor
The urcu-common library contains common code like the write-free queue
and compat code, each urcu flavor library is dynamicly linked with it.
Most but not all toolchains will automatically link an executable with a
transitive depency of an explicitly linked library if said binary uses a
symbol from the transitive dependency.
Since this behavior is not present in all toolchains, add
'-lurcu-common' to the 'Libs' field of each flavors pkg-config file so
that executables using symbols from urcu-common can be reliably linked
using pkg-config.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Paul E. McKenney [Thu, 22 Oct 2020 22:30:21 +0000 (15:30 -0700)]
call_rcu: Fix race between rcu_barrier() and call_rcu_data_free()
The current code can lose RCU callbacks at shutdown time, which can
result in hangs. This lossage can happen as follows:
o A thread invokes call_rcu_data_free(), which executes up through
the wake_call_rcu_thread(). At this point, the call_rcu_data
structure has been drained of callbacks, but is still on the
call_rcu_data_list. Note that this thread does not hold the
call_rcu_mutex.
o Another thread invokes rcu_barrier(), which traverses the
call_rcu_data_list under the protection of call_rcu_mutex,
a list which still includes the above newly drained structure.
This thread therefore adds a callback to the newly drained
call_rcu_data structure. It then releases call_rcu_mutex and
enters a mystifying loop that does futex stuff.
o The first thread finishes executing call_rcu_data_free(),
which acquires call_rcu_mutex just long enough to remove the
newly drained call_rcu_data structure from call_rcu_data_list.
Which causes one of the rcu_barrier() invocation's callbacks to
be leaked.
o The second thread's rcu_barrier() invocation never returns
resulting in a hang.
This commit therefore changes call_rcu_data_free() to acquire
call_rcu_mutex before checking the call_rcu_data structure for callbacks.
In the case where there are no callbacks, call_rcu_mutex is held across
both the check and the removal from call_rcu_data_list, thus preventing
rcu_barrier() from adding a callback in the meantime. In the case where
there are callbacks, call_rcu_mutex must be momentarily dropped across
the call to get_default_call_rcu_data(), which can itself acquire
call_rcu_mutex. This momentary drop is not a problem because any
callbacks that rcu_barrier() might queue during that period of time will
be moved to the default call_rcu_data structure, and the lock will be
held across the full time including moving those callbacks and removing
the call_rcu_data structure that was passed into call_rcu_data_free()
from call_rcu_data_list.
With this fix, a several-hundred-CPU test successfully completes more
than 5,000 executions. Without this fix, it fails within a few tens
of executions. Although the failures happen more quickly on larger
systems, in theory this could happen on a single-CPU system, courtesy
of preemption.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Stephen Hemminger <stephen@networkplumber.org> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: <lttng-dev@lists.lttng.org> Cc: <linux-kernel@vger.kernel.org> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Fix: tls-compat.h exposes compiler-dependent public configuration
Exposing the storage class chosen by ax_tls.m4 in a public header is
a bad idea, because if a recent gcc is used when configuring
liburcu, thus detecting C11, it will choose _Thread_local. Then, if an
external project uses urcu/tls-compat.h with an older gcc (e.g. 4.8),
it will fail to build, because that storage class is unknown, and
__thread should be used instead.
Therefore, use a preprocessor conditional on __cplusplus to detect C++11
(and use thread_local). Else, the STDC version is used to select
_Thread_local. Else check if _MSC_VER is defined to select
__declspec(thread), or else rely on __thread as fallback.
On architectures where "char" is signed, it should be cast to unsigned
char before being passed as parameter to isdigit or isspace. Based on
their man page:
These functions check whether c, which must have the value of an
unsigned char or EOF, falls into a certain character class according to
the specified locale.
Passing a signed char as parameter is invalid if the values fall into
the negative range of the signed char.
urcu-bp: perform thread registration on urcu_bp_register_thread
Some real-time use-cases (e.g. Xenomai) require to perform urcu-bp
thread registration early in the thread life-time before it starts
performing real-time tasks.
Currently, this can be achieved by issuing a urcu_bp_read_lock() and
urcu_bp_read_unlock() pair, or by using urcu_bp_read_ongoing(), while in
the initialization phrase.
However, it seems natural to expect that calling urcu_bp_register_thread()
would have the side effect to perform the lazy thread registration
immediately rather than being a no-op.
cds_lfht_is_node_deleted parameter can be marked const
Mark the cds_lfht_node pointer parameter of cds_lfht_is_node_deleted
as const. The fact that this parameter is mutable makes it harder to
use liburcu in const-correct code.
In urcu-signal flavor, call_rcu_thread calls synchronize_rcu which
will send SIGRCU signal to all registed threads, and then loops to
wait need_mb to be cleared. However, the registed workqueue_thread
does not process the SIGRCU signal, and never clear the need_mb.
Based on above, call_rcu_thread and workqueue_thread will wait
forever for completion of the grace period: call_rcu_thread which holds
the rcu_registry_lock, waits for workqueue_thread to do cmm_smp_mb.
While workqueue thread never does cmm_smp_mb because of signal blocking,
and it will eventually wait to get rcu_registry_lock in do_resize_cb.
The phenomenon is as follows, which is easy to be triggered:
(gdb) t 2
[Switching to thread 2 (Thread 0xffff83c3b080 (LWP 27116))]
0 0x0000ffff845296c4 in poll () from /lib64/libc.so.6
(gdb) bt
0 0x0000ffff845296c4 in poll () from /lib64/libc.so.6
1 0x0000ffff8461b93c in force_mb_all_readers () at urcu.c:241
2 0x0000ffff8461c748 in smp_mb_master () at urcu.c:249
3 urcu_signal_synchronize_rcu () at urcu.c:445
4 0x0000ffff8461d004 in call_rcu_thread at urcu-call-rcu-impl.h:364
5 0x0000ffff845eb8bc in start_thread () from /lib64/libpthread.so.0
6 0x0000ffff845335cc in thread_start () from /lib64/libc.so.6
(gdb) t 3
[Switching to thread 3 (Thread 0xffff8443c080 (LWP 27191))]
0 0x0000ffff845f51c4 in __lll_lock_wait () from /lib64/libpthread.so.0
(gdb) bt
0 0x0000ffff845f51c4 in __lll_lock_wait () from /lib64/libpthread.so.0
1 0x0000ffff845ee048 in pthread_mutex_lock () from /lib64/libpthread.so.0
2 0x0000ffff8461b814 in mutex_lock ( <rcu_registry_lock>) at urcu.c:157
3 0x0000ffff8461b9e4 in urcu_signal_unregister_thread () at urcu.c:564
4 0x0000ffff8463e62c in do_resize_cb (work=0x11e2e790) at rculfhash.c:2042
5 0x0000ffff8463c940 in workqueue_thread (arg=0x11e1d260) at workqueue.c:228
6 0x0000ffff845eb8bc in start_thread () from /lib64/libpthread.so.0
7 0x0000ffff845335cc in thread_start () from /lib64/libc.so.6
So we should not block SIGRCU in workqueue thread to avoid blocking
forever in the grace period awaiting on the worker thread when using
urcu-signal flavor.
Signed-off-by: hewenliang <hewenliang4@huawei.com> Co-developed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Found by Coverity:
CID 1357055 (#1 of 1): Unchecked return value (CHECKED_RETURN)
4. check_return: Calling pthread_mutex_lock without checking return value
(as is done elsewhere 44 out of 48 times).
Michael Jeanson [Mon, 3 Jun 2019 20:36:43 +0000 (16:36 -0400)]
Fix: SONAME bump to 6.1.0
In commit d6c78161aed9b2d550ce201b0a8cd5b3ee515ac8 we bumped the 'age'
part of the library version with the intention of keeping the same major
SONAME because we only introduced new symbols. However by bumping the
'age' and not the 'current' we substracted 1 to the major SONAME which
we did not intend. Seems like we missed this in testing.
Fix it by bumping the 'current' to end up with an SONAME of 6.1.0 which
is what we originally intended.
From the libtool manual for reference :
Programs using the previous version may use the new version as drop-in
replacement, but programs using the new version may use APIs not present
in the previous one. In other words, a program linking against the new
version may fail with “unresolved symbols” if linking against the old
version at runtime: set revision to 0, bump current and age.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cleanup: update code layout to fix old gcc warning
Some CI jobs show:
urcu-pointer.o
13:46:22 In file included from urcu.c:49:0:
13:46:22 urcu-wait.h:70:9: warning: missing initializer for field 'lock' of 'struct cds_wfs_stack' [-Wmissing-field-initializers]
13:46:22 struct urcu_wait_queue name = URCU_WAIT_QUEUE_HEAD_INIT(name)
13:46:22 ^
13:46:22 urcu.c:150:8: note: in expansion of macro 'DEFINE_URCU_WAIT_QUEUE'
13:46:22 static DEFINE_URCU_WAIT_QUEUE(gp_waiters);
13:46:22 ^
13:46:22 In file included from urcu-wait.h:27:0,
13:46:22 from urcu.c:49:
13:46:22 ../include/urcu/wfstack.h:92:18: note: 'lock' declared here
13:46:22 pthread_mutex_t lock;
13:46:22
Building liburcu with --enable-cds-lfht-iter-debug and rebuilding
application to match the ABI change allows finding cases where the
hash table iterator is re-purposed to be used on a different hash
table while still being used to iterate on a hash table.
This is a common programming mistake that happens often enough
to justify creating a debugging mode to track this automatically.
Michael Jeanson [Wed, 12 Dec 2018 20:01:37 +0000 (15:01 -0500)]
Port: no symbols aliases on MacOS
There is no equivalent to symbols aliases on MacOS, this will
unfortunatly break the ABI for SONAME(6) and will require a rebuild of
client applications.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Fri, 30 Nov 2018 19:28:51 +0000 (14:28 -0500)]
Add -Wextra to CFLAGS
Edited by Mathieu Desnoyers:
Use /* fall through */ rather than __attribute__((fallthrough)) to
stay compatible with clang and gcc < 7. The fallthrough attribute
was introduced in gcc 7.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Use new header locations for includes from urcu code
This also moves urcu/static/urcu-pointer.h to urcu/static/pointer.h.
Considering that it is not meant to be included directly by library
users, it should not cause any problem.
urcu-call-rcu.h is included by rculfhqueue.h only for struct rcu_head
forward declaration, but as a result the urcu flavor needs to be chosen
beforehand, and therefore prevents using rculfqueue.h with multiple
urcu flavors in a given compile unit.
Remove that include and do a forward declaration of struct rcu_head
instead.
The header include/urcu/urcu.h now includes the right header between the
memb, signal, or mb flavors based on the compiler defines.
The symbol names of liburcu flavors are cleaned up, favoring the
following hierarchy:
urcu_<flavor name>_...
This is an ABI-breaking change, however the previous symbols name were
kept as aliases to maintain backward compatibility. They will be removed
when the next SONAME bump occurs.
The new liburcu-memb.so shared object is introduced, properly
namespacing this flavor. It is a duplicate of the previous liburcu.so,
which is kept around for backward compatibility.
The new URCU_API_MAP macro is introduced, controlling whether the
urcu API "mapping" should stay defined after inclusion of the flavor
headers. Users wishing to use the prior urcu API should either
explicitly define URCU_API_MAP before including the urcu/urcu*.h flavor
headers, or include the flavor header files from the include toplevel
directory, which are placeholders for backward compatibility. Use of
many urcu flavors within the same _LGPL_SOURCE compile unit should not
use the "map" APIs.
Internally, the "map" header files are split into one header per
flavor. The include guards are removed, so their effect can be
applied more than once. A new include/urcu/map/clear.h header is
introduced, which undefines the mappings at the end of the flavor
header if URCU_API_MAP is not set.
The new APIs namespaced for each urcu flavor is the recommended way to
use liburcu. We can expect the prior APIs to eventually become
deprecated over time.
Fix: only wait if work queue is empty in real-time mode
Unconditionally waiting for 10 ms after the completion of every batch
of jobs of the work queue in real-time mode appears to be a behaviour
inherited from the call-rcu thread.
While this is a fair trade-off in the context of call-rcu, it is less
evident that it is desirable in the context of a general-purpose
work queue. Waiting when work is available artificially degrades the
latency characteristics of the work queue.
If a workqueue user even need the explicit delay for batching (e.g. if
a call-rcu implementation would ever use the workqueue worker thread),
it can add it within the worker_before_wait_fct callback received as
argument from workqueue creation.
Fix: don't wait after completion of a work queue job batch
As indicated in the previous patch of this series, waiting on
completion of a job batch from the work queue artificially increases
the latency of the work queue.
The previous patch removed the wait that is performed when the
work queue is observed to be empty and was observed as the cause of a
performance problem.
It is likely that waiting when the queue is observed to be non-empty
is similarly unintended. Note that I have not observed such a problem
myself.
If a workqueue user even need the explicit delay for batching (e.g. if
a call-rcu implementation would ever use the workqueue worker thread),
it can add it within the worker_before_wait_fct callback received as
argument from workqueue creation.
Fix: don't wait after completion of job batch if work queue is empty
On completion of a batch of jobs from the work queue, a wait of 10
ms (using poll()) is performed if there is no work present in the
work queue before waiting on its futex.
The work queue thread's structure is inspired by the call-rcu thread.
In the context of the call-rcu thread, my understanding is that the
intention is to ensure that the thread does not continuously wake-up
to process a single queued item. This is fine as an application should
not wait for a call-rcu job to be executed (or at least I don't see a
use-case for that).
In the context of the work queue, waiting for more work to be available
artificially slows down the execution of work on which an application
may wait.
I have observed a case where LTTng's session daemon's shutdown is
takes around 4 seconds as a large number of cds_lfht objects are
destroyed. Removing the wait reduces the duration of this phase of the
shut-down to almost ~10ms.
If a workqueue user even need the explicit delay for batching (e.g. if
a call-rcu implementation would ever use the workqueue worker thread),
it can add it within the worker_before_wait_fct callback received as
argument from workqueue creation.
Fix: mixup between URCU_WORKQUEUE_RT and URCU_CALL_RCU_RT
The work queue implementation is derived from the call-rcu thread. A
number of references seem to have been left in place when adapting the
code for its new purpose.
The URCU_CALL_RCU_RT flag is used by wake_worker_thread() while the
rest of the workqueue.c code uses URCU_WORKQUEUE_RT to determine if
the work queue was configured in real-time mode. Both flags are defined
to the same value (0x1) and the current internal user of the
work queue (lfht) never specifies any flags.
In practice, this does not cause any problem, but this mixup should
be fixed nevertheless.
Michael Jeanson [Fri, 23 Nov 2018 21:47:18 +0000 (16:47 -0500)]
Fix: pthread_rwlock initialization on Cygwin
On Cygwin the PTHREAD_RWLOCK_INITIALIZER macro is not
sufficient to get a properly initialized pthread_rwlock_t
struct. Use the pthread_rwlock_init function instead which
should work on all platforms.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Fri, 23 Nov 2018 20:27:04 +0000 (15:27 -0500)]
Fix: compat_futex_noasync on Cygwin
The futex_noasync compat code uses a weak symbol to share state across
different shared object which is not possible on Windows with the
Portable Executable format. Use the async compat code for both cases.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Eric Wong [Wed, 1 Aug 2018 18:54:45 +0000 (18:54 +0000)]
wfcqueue: allow defining CDS_WFCQ_WAIT_SLEEP to override `poll'
Users may want to use alternative sleeping behavior instead of
`poll'. Make CDS_WFCQ_WAIT_SLEEP a macro which may be defined
before including wfcqueue.h.
This alternative behavior could include logging, performing
low-priority cleanup work, sleeping a shorter/longer interval
or any combination of that.
This will also make integration into glibc easier, as `poll'
linkage causes conformance test failures even when relegated
to an impossible code path:
https://public-inbox.org/libc-alpha/20180801092626.jrwyrojfye4avcis@whir/
Signed-off-by: Eric Wong <normalperson@yhbt.net> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Fri, 8 Dec 2017 16:00:17 +0000 (11:00 -0500)]
Tests: Replace prove by autotools tap runner
This patch removes the dependency on the prove perl script
to run the TAP test suite. It replaces it with the autotools
shell TAP driver that only requires a shell and awk.
Custom arguments can be passed to the test runner with
env variables as follow:
env LOG_DRIVER_FLAGS='--comments --ignore-exit' \
TESTS='foo.test baz.test' make -e check
This tap driver also creates a log file for each test that
can then be used by another system to build a test report.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
liburcu-bp: Use membarrier private expedited when available
For the liburcu-bp flavor, use the membarrier private expedited command
when available. It is faster than the shared expedited command, but has
only been introduced in 4.14 Linux kernels.
When configured with --disable-sys-membarrier-fallback, liburcu-bp
will abort if running on a kernel that do not provide the membarrier
private expedited command (e.g. CONFIG_MEMBARRIER=n or kernel version
below 4.14).
liburcu: Use membarrier private expedited when available
For the liburcu flavor, use the membarrier private expedited
command when available. It is faster than the shared expedited
command, but has only been introduced in 4.14 Linux kernels.
When configured with --disable-sys-membarrier-fallback, liburcu
will abort if running on a kernel that provide neither the shared
nor the private expedited membarrier commands. This is the case
if running on a CONFIG_MEMBARRIER=n kernel, or a kernel version
below 4.3.
Michael Jeanson [Fri, 28 Jul 2017 15:51:15 +0000 (11:51 -0400)]
Fix: don't use overlapping mmap mappings on Cygwin
The allocation scheme used by the mmap based RCU hash table is to make a
large unaccessible mapping to reserve memory without allocating it.
Then smaller chunks are allocated by overlapping read/write mappings which
do allocate memory. Deallocation is done by an overlapping unaccessible
mapping.
This scheme was tested on Linux, macOS and Solaris. However, on Cygwin the
mmap wrapper is based on the Windows NtMapViewOfSection API which doesn't
support overlapping mappings.
An alternative to the overlapping mappings is to use mprotect to change the
protection on chunks of the large mapping, read/write to allocate and none
to deallocate. This works perfecty on Cygwin and Solaris but on Linux a
call to madvise is also required to deallocate and it just doesn't work on
macOS.
For this reason, we keep to original scheme on all platforms except Cygwin.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Michael Jeanson [Wed, 26 Jul 2017 17:31:04 +0000 (13:31 -0400)]
Tests fix: errors in shell scripts
Fix all shellcheck errors in the test scripts, switch to posix
compatible syntax. Remove duplicated code already included in common.sh.
Call the tap.sh cleanup code from our exit trap instead of overriding
it.
Signed-off-by: Michael Jeanson <mjeanson@efficios.com> Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
The initial-exec model seems to behave differently than global-dynamic
with respect to lazy initialization, causing locks to be taken then
first time each thread touch the TLS. This introduces deadlocks
with library constructors waiting on other threads.
The initial-exec tls model removes requirement on performing memory
allocation the first time a tls variable is touched by any given thread.
This is needed to ensure usage of the TLS from a signal handler works
fine.
Given that the link-editor figures out the right model to use at
runtime, we can change the tls model without changing the soname major
version.
This also brings interesting speedups over the GD model. This does not
affects TLS accesses performed by executables, but does affect TLS
accesses performed by libraries.
Fix: don't use membarrier SHARED syscall command in liburcu-bp
One main user of liburcu-bp (lttng-ust) invokes synchronize_rcu()
repeatedly, without batching (does not use call_rcu).
Those delays introduced by sys_membarrier SHARED command significantly
impacts application startup time. Therefore, revert to not using the
membarrier SHARED command.
The RCU lock-free hash table currently requires that the destroy
function should not be called from within RCU read-side critical
sections. This is caused by the lazy resize, which uses the call_rcu
worker thread, even though all it really needs is a workqueue/worker
thread scheme.
Use the new internal workqueue API instead of call_rcu in rculfhash to
overcome this limitation.
projects / userspace-rcu.git / log
