X-Git-Url: https://git.lttng.org/?p=urcu.git;a=blobdiff_plain;f=urcu-call-rcu-impl.h;h=6fcf8c897c9b437acd04b111a8d8beea1c377c8d;hp=f1e46fe3e7494cb6c463bbc76b2b11bdabf2a947;hb=bc94ca9bada25f7403e3e859caa241146ae8e338;hpb=c1d2c60b1c754815d27f29705d5f2077c0900148

diff --git a/urcu-call-rcu-impl.h b/urcu-call-rcu-impl.h
index f1e46fe..6fcf8c8 100644
--- a/urcu-call-rcu-impl.h
+++ b/urcu-call-rcu-impl.h
@@ -39,15 +39,15 @@
 #include "urcu-call-rcu.h"
 #include "urcu-pointer.h"
 #include "urcu/list.h"
+#include "urcu/urcu-futex.h"
 
 /* Data structure that identifies a call_rcu thread. */
 
 struct call_rcu_data {
 	struct cds_wfq_queue cbs;
 	unsigned long flags;
-	pthread_mutex_t mtx;
-	pthread_cond_t cond;
-	unsigned long qlen;
+	int futex;
+	unsigned long qlen; /* maintained for debugging. */
 	pthread_t tid;
 	int cpu_affinity;
 	struct cds_list_head list;
@@ -88,6 +88,26 @@ static struct call_rcu_data *default_call_rcu_data;
 static struct call_rcu_data **per_cpu_call_rcu_data;
 static long maxcpus;
 
+static void call_rcu_wait(struct call_rcu_data *crdp)
+{
+	/* Read call_rcu list before read futex */
+	cmm_smp_mb();
+	if (uatomic_read(&crdp->futex) == -1)
+		futex_async(&crdp->futex, FUTEX_WAIT, -1,
+		      NULL, NULL, 0);
+}
+
+static void call_rcu_wake_up(struct call_rcu_data *crdp)
+{
+	/* Write to call_rcu list before reading/writing futex */
+	cmm_smp_mb();
+	if (unlikely(uatomic_read(&crdp->futex) == -1)) {
+		uatomic_set(&crdp->futex, 0);
+		futex_async(&crdp->futex, FUTEX_WAKE, 1,
+		      NULL, NULL, 0);
+	}
+}
+
 /* Allocate the array if it has not already been allocated. */
 
 static void alloc_cpu_call_rcu_data(void)
@@ -183,6 +203,7 @@ static void *call_rcu_thread(void *arg)
 	struct cds_wfq_node **cbs_tail;
 	struct call_rcu_data *crdp = (struct call_rcu_data *)arg;
 	struct rcu_head *rhp;
+	int rt = !!(uatomic_read(&crdp->flags) & URCU_CALL_RCU_RT);
 
 	if (set_thread_cpu_affinity(crdp) != 0) {
 		perror("pthread_setaffinity_np");
@@ -190,6 +211,11 @@ static void *call_rcu_thread(void *arg)
 	}
 
 	thread_call_rcu_data = crdp;
+	if (!rt) {
+		uatomic_dec(&crdp->futex);
+		/* Decrement futex before reading call_rcu list */
+		cmm_smp_mb();
+	}
 	for (;;) {
 		if (&crdp->cbs.head != _CMM_LOAD_SHARED(crdp->cbs.tail)) {
 			while ((cbs = _CMM_LOAD_SHARED(crdp->cbs.head)) == NULL)
@@ -214,29 +240,32 @@ static void *call_rcu_thread(void *arg)
 			} while (cbs != NULL);
 			uatomic_sub(&crdp->qlen, cbcount);
 		}
-		if (crdp->flags & URCU_CALL_RCU_STOP)
+		if (uatomic_read(&crdp->flags) & URCU_CALL_RCU_STOP)
 			break;
-		if (crdp->flags & URCU_CALL_RCU_RT)
-			poll(NULL, 0, 10);
-		else {
-			call_rcu_lock(&crdp->mtx);
-			_CMM_STORE_SHARED(crdp->flags,
-				     crdp->flags & ~URCU_CALL_RCU_RUNNING);
-			if (&crdp->cbs.head ==
-			    _CMM_LOAD_SHARED(crdp->cbs.tail) &&
-			    pthread_cond_wait(&crdp->cond, &crdp->mtx) != 0) {
-				perror("pthread_cond_wait");
-				exit(-1);
+		if (!rt) {
+			if (&crdp->cbs.head
+			    == _CMM_LOAD_SHARED(crdp->cbs.tail)) {
+				call_rcu_wait(crdp);
+				poll(NULL, 0, 10);
+				uatomic_dec(&crdp->futex);
+				/*
+				 * Decrement futex before reading
+				 * call_rcu list.
+				 */
+				cmm_smp_mb();
 			}
-			_CMM_STORE_SHARED(crdp->flags,
-				     crdp->flags | URCU_CALL_RCU_RUNNING);
+		} else {
 			poll(NULL, 0, 10);
-			call_rcu_unlock(&crdp->mtx);
 		}
 	}
-	call_rcu_lock(&crdp->mtx);
-	crdp->flags |= URCU_CALL_RCU_STOPPED;
-	call_rcu_unlock(&crdp->mtx);
+	if (!rt) {
+		/*
+		 * Read call_rcu list before write futex.
+		 */
+		cmm_smp_mb();
+		uatomic_set(&crdp->futex, 0);
+	}
+	uatomic_or(&crdp->flags, URCU_CALL_RCU_STOPPED);
 	return NULL;
 }
 
@@ -260,15 +289,8 @@ static void call_rcu_data_init(struct call_rcu_data **crdpp,
 	memset(crdp, '\0', sizeof(*crdp));
 	cds_wfq_init(&crdp->cbs);
 	crdp->qlen = 0;
-	if (pthread_mutex_init(&crdp->mtx, NULL) != 0) {
-		perror("pthread_mutex_init");
-		exit(-1);
-	}
-	if (pthread_cond_init(&crdp->cond, NULL) != 0) {
-		perror("pthread_cond_init");
-		exit(-1);
-	}
-	crdp->flags = flags | URCU_CALL_RCU_RUNNING;
+	crdp->futex = 0;
+	crdp->flags = flags;
 	cds_list_add(&crdp->list, &call_rcu_data_list);
 	crdp->cpu_affinity = cpu_affinity;
 	cmm_smp_mb();  /* Structure initialized before pointer is planted. */
@@ -492,16 +514,8 @@ int create_all_cpu_call_rcu_data(unsigned long flags)
  */
 static void wake_call_rcu_thread(struct call_rcu_data *crdp)
 {
-	if (!(_CMM_LOAD_SHARED(crdp->flags) & URCU_CALL_RCU_RT)) {
-		call_rcu_lock(&crdp->mtx);
-		if (!(_CMM_LOAD_SHARED(crdp->flags) & URCU_CALL_RCU_RUNNING)) {
-			if (pthread_cond_signal(&crdp->cond) != 0) {
-				perror("pthread_cond_signal");
-				exit(-1);
-			}
-		}
-		call_rcu_unlock(&crdp->mtx);
-	}
+	if (!(_CMM_LOAD_SHARED(crdp->flags) & URCU_CALL_RCU_RT))
+		call_rcu_wake_up(crdp);
 }
 
 /*
@@ -557,12 +571,10 @@ void call_rcu_data_free(struct call_rcu_data *crdp)
 	if (crdp == NULL || crdp == default_call_rcu_data) {
 		return;
 	}
-	if ((crdp->flags & URCU_CALL_RCU_STOPPED) == 0) {
-		call_rcu_lock(&crdp->mtx);
-		crdp->flags |= URCU_CALL_RCU_STOP;
-		call_rcu_unlock(&crdp->mtx);
+	if ((uatomic_read(&crdp->flags) & URCU_CALL_RCU_STOPPED) == 0) {
+		uatomic_or(&crdp->flags, URCU_CALL_RCU_STOP);
 		wake_call_rcu_thread(crdp);
-		while ((crdp->flags & URCU_CALL_RCU_STOPPED) == 0)
+		while ((uatomic_read(&crdp->flags) & URCU_CALL_RCU_STOPPED) == 0)
 			poll(NULL, 0, 1);
 	}
 	if (&crdp->cbs.head != _CMM_LOAD_SHARED(crdp->cbs.tail)) {
@@ -646,7 +658,7 @@ void call_rcu_after_fork_child(void)
 		if (crdp == default_call_rcu_data)
 			crdp = cds_list_entry(crdp->list.prev,
 					      struct call_rcu_data, list);
-		crdp->flags = URCU_CALL_RCU_STOPPED;
+		uatomic_set(&crdp->flags, URCU_CALL_RCU_STOPPED);
 		call_rcu_data_free(crdp);
 	}
 }