Rewrite ethread library

Large parts of the ethread library have been rewritten. The
ethread library is an Erlang runtime system internal, portable
thread library used by the runtime system itself.

Most notable improvement is a reader optimized rwlock
implementation which dramatically improve the performance of
read-lock/read-unlock operations on multi processor systems by
avoiding ping-ponging of the rwlock cache lines. The reader
optimized rwlock implementation is used by miscellaneous
rwlocks in the runtime system that are known to be read-locked
frequently, and can be enabled on ETS tables by passing the
`{read_concurrency, true}' option upon table creation. See the
documentation of `ets:new/2' for more information.

The ethread library can now also use the libatomic_ops library
for atomic memory accesses. This makes it possible for the
Erlang runtime system to utilize optimized atomic operations
on more platforms than before. Use the
`--with-libatomic_ops=PATH' configure command line argument
when specifying where the libatomic_ops installation is
located. The libatomic_ops library can be downloaded from:
http://www.hpl.hp.com/research/linux/atomic_ops/

The changed API of the ethread library has also caused
modifications in the Erlang runtime system. Preparations for
the to come "delayed deallocation" feature has also been done
since it depends on the ethread library.

Note: When building for x86, the ethread library will now use
instructions that first appeared on the pentium 4 processor. If
you want the runtime system to be compatible with older
processors (back to 486) you need to pass the
`--enable-ethread-pre-pentium4-compatibility' configure command
line argument when configuring the system.

1 files changed, 9 insertions, 9 deletions

diff --git a/erts/emulator/beam/erl_lock_count.c b/erts/emulator/beam/erl_lock_count.c
index 26028aeefc..239773f366 100644
--- a/erts/emulator/beam/erl_lock_count.c
+++ b/erts/emulator/beam/erl_lock_count.c
@@ -166,8 +166,8 @@ static void print_lock_x(erts_lcnt_lock_t *lock, Uint16 flag, char *action, char
     int i;
     
     type = lcnt_lock_type(lock->flag);
-    ethr_atomic_read(&lock->r_state, &r_state);
-    ethr_atomic_read(&lock->w_state, &w_state);
+    r_state = ethr_atomic_read(&lock->r_state);
+    w_state = ethr_atomic_read(&lock->w_state);
 
     
     if (lock->flag & flag) {
@@ -394,10 +394,10 @@ void erts_lcnt_lock_opt(erts_lcnt_lock_t *lock, Uint16 option) {
 
     ASSERT(eltd);
     
-    ethr_atomic_read(&lock->w_state, &w_state);
+    w_state = ethr_atomic_read(&lock->w_state);
     
     if (option & ERTS_LCNT_LO_WRITE) {
-        ethr_atomic_read(&lock->r_state, &r_state);
+        r_state = ethr_atomic_read(&lock->r_state);
         ethr_atomic_inc( &lock->w_state);
     }
     if (option & ERTS_LCNT_LO_READ) {
@@ -423,7 +423,7 @@ void erts_lcnt_lock(erts_lcnt_lock_t *lock) {
     
     if (erts_lcnt_rt_options & ERTS_LCNT_OPT_SUSPEND) return;
 
-    ethr_atomic_read(&lock->w_state, &w_state);
+    w_state = ethr_atomic_read(&lock->w_state);
     ethr_atomic_inc( &lock->w_state);
 
     eltd = lcnt_get_thread_data();
@@ -478,7 +478,7 @@ void erts_lcnt_lock_post_x(erts_lcnt_lock_t *lock, char *file, unsigned int line
     
 #ifdef DEBUG
     if (!(lock->flag & (ERTS_LCNT_LT_RWMUTEX | ERTS_LCNT_LT_RWSPINLOCK))) {
-    	ethr_atomic_read(&lock->flowstate, &flowstate);
+	flowstate = ethr_atomic_read(&lock->flowstate);
 	ASSERT(flowstate == 0);
     	ethr_atomic_inc( &lock->flowstate);
     }
@@ -522,12 +522,12 @@ void erts_lcnt_unlock(erts_lcnt_lock_t *lock) {
     if (erts_lcnt_rt_options & ERTS_LCNT_OPT_SUSPEND) return;
 #ifdef DEBUG
     /* flowstate */
-    ethr_atomic_read(&lock->flowstate, &flowstate);
+    flowstate = ethr_atomic_read(&lock->flowstate);
     ASSERT(flowstate == 1);
     ethr_atomic_dec( &lock->flowstate);
     
     /* write state */
-    ethr_atomic_read(&lock->w_state, &w_state);
+    w_state = ethr_atomic_read(&lock->w_state);
     ASSERT(w_state > 0)
 #endif
     ethr_atomic_dec(&lock->w_state);
@@ -558,7 +558,7 @@ void erts_lcnt_trylock(erts_lcnt_lock_t *lock, int res) {
     if (res != EBUSY) {
 	
 #ifdef DEBUG
-    	ethr_atomic_read(&lock->flowstate, &flowstate);
+	flowstate = ethr_atomic_read(&lock->flowstate);
 	ASSERT(flowstate == 0);
     	ethr_atomic_inc( &lock->flowstate);
 #endif