[dpdk-dev,v13,02/14] eal/linux: add rte_epoll_wait/ctl support

diff --git a/lib/librte_eal/linuxapp/eal/eal_interrupts.c b/lib/librte_eal/linuxapp/eal/eal_interrupts.c
index a6325c6..dc327a4 100644
--- a/lib/librte_eal/linuxapp/eal/eal_interrupts.c
+++ b/lib/librte_eal/linuxapp/eal/eal_interrupts.c
@@ -69,6 +69,8 @@ 
 
 #define EAL_INTR_EPOLL_WAIT_FOREVER (-1)
 
+static RTE_DEFINE_PER_LCORE(int, _epfd) = -1; /**< epoll fd per thread */
+
 /**
  * union for pipe fds.
  */
@@ -894,3 +896,140 @@  rte_eal_intr_init(void)
 
 	return -ret;
 }
+
+static int
+eal_epoll_process_event(struct epoll_event *evs, unsigned int n,
+			struct rte_epoll_event *events)
+{
+	unsigned int i, count = 0;
+	struct rte_epoll_event *rev;
+
+	for (i = 0; i < n; i++) {
+		rev = evs[i].data.ptr;
+		if (!rev || !rte_atomic32_cmpset(&rev->status, RTE_EPOLL_VALID,
+						 RTE_EPOLL_EXEC))
+			continue;
+
+		events[count].status        = RTE_EPOLL_VALID;
+		events[count].fd            = rev->fd;
+		events[count].epfd          = rev->epfd;
+		events[count].epdata.event  = rev->epdata.event;
+		events[count].epdata.data   = rev->epdata.data;
+		if (rev->epdata.cb_fun)
+			rev->epdata.cb_fun(rev->fd,
+					   rev->epdata.cb_arg);
+
+		rte_compiler_barrier();
+		rev->status = RTE_EPOLL_VALID;
+		count++;
+	}
+	return count;
+}
+
+static inline int
+eal_init_tls_epfd(void)
+{
+	int pfd = epoll_create(255);
+
+	if (pfd < 0) {
+		RTE_LOG(ERR, EAL,
+			"Cannot create epoll instance\n");
+		return -1;
+	}
+	return pfd;
+}
+
+int
+rte_intr_tls_epfd(void)
+{
+	if (RTE_PER_LCORE(_epfd) == -1)
+		RTE_PER_LCORE(_epfd) = eal_init_tls_epfd();
+
+	return RTE_PER_LCORE(_epfd);
+}
+
+int
+rte_epoll_wait(int epfd, struct rte_epoll_event *events,
+	       int maxevents, int timeout)
+{
+	struct epoll_event evs[maxevents];
+	int rc;
+
+	if (!events) {
+		RTE_LOG(ERR, EAL, "rte_epoll_event can't be NULL\n");
+		return -1;
+	}
+
+	/* using per thread epoll fd */
+	if (epfd == RTE_EPOLL_PER_THREAD)
+		epfd = rte_intr_tls_epfd();
+
+	while (1) {
+		rc = epoll_wait(epfd, evs, maxevents, timeout);
+		if (likely(rc > 0)) {
+			/* epoll_wait has at least one fd ready to read */
+			rc = eal_epoll_process_event(evs, rc, events);
+			break;
+		} else if (rc < 0) {
+			if (errno == EINTR)
+				continue;
+			/* epoll_wait fail */
+			RTE_LOG(ERR, EAL, "epoll_wait returns with fail %s\n",
+				strerror(errno));
+			rc = -1;
+			break;
+		}
+	}
+
+	return rc;
+}
+
+static inline void
+eal_epoll_data_safe_free(struct rte_epoll_event *ev)
+{
+	while (!rte_atomic32_cmpset(&ev->status, RTE_EPOLL_VALID,
+				    RTE_EPOLL_INVALID))
+		while (ev->status != RTE_EPOLL_VALID)
+			rte_pause();
+	memset(&ev->epdata, 0, sizeof(ev->epdata));
+	ev->fd = -1;
+	ev->epfd = -1;
+}
+
+int
+rte_epoll_ctl(int epfd, int op, int fd,
+	      struct rte_epoll_event *event)
+{
+	struct epoll_event ev;
+
+	if (!event) {
+		RTE_LOG(ERR, EAL, "rte_epoll_event can't be NULL\n");
+		return -1;
+	}
+
+	/* using per thread epoll fd */
+	if (epfd == RTE_EPOLL_PER_THREAD)
+		epfd = rte_intr_tls_epfd();
+
+	if (op == EPOLL_CTL_ADD) {
+		event->status = RTE_EPOLL_VALID;
+		event->fd = fd;  /* ignore fd in event */
+		event->epfd = epfd;
+		ev.data.ptr = (void *)event;
+	}
+
+	ev.events = event->epdata.event;
+	if (epoll_ctl(epfd, op, fd, &ev) < 0) {
+		RTE_LOG(ERR, EAL, "Error op %d fd %d epoll_ctl, %s\n",
+			op, fd, strerror(errno));
+		if (op == EPOLL_CTL_ADD)
+			/* rollback status when CTL_ADD fail */
+			event->status = RTE_EPOLL_INVALID;
+		return -1;
+	}
+
+	if (op == EPOLL_CTL_DEL && event->status != RTE_EPOLL_INVALID)
+		eal_epoll_data_safe_free(event);
+
+	return 0;
+}
diff --git a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
index b6f2c41..4db95bb 100644
--- a/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
+++ b/lib/librte_eal/linuxapp/eal/include/exec-env/rte_interrupts.h
@@ -51,6 +51,32 @@  enum rte_intr_handle_type {
 	RTE_INTR_HANDLE_MAX
 };
 
+#define RTE_INTR_EVENT_ADD            1UL
+#define	RTE_INTR_EVENT_DEL            2UL
+
+typedef void (*rte_intr_event_cb_t)(int fd, void *arg);
+
+struct rte_epoll_data {
+	uint32_t event;               /**< event type */
+	void *data;                   /**< User data */
+	rte_intr_event_cb_t cb_fun;   /**< IN: callback fun */
+	void *cb_arg;	              /**< IN: callback arg */
+};
+
+enum {
+	RTE_EPOLL_INVALID = 0,
+	RTE_EPOLL_VALID,
+	RTE_EPOLL_EXEC,
+};
+
+/** interrupt epoll event obj, taken by epoll_event.ptr */
+struct rte_epoll_event {
+	volatile uint32_t status;  /**< OUT: event status */
+	int fd;                    /**< OUT: event fd */
+	int epfd;       /**< OUT: epoll instance the ev associated with */
+	struct rte_epoll_data epdata;
+};
+
 /** Handle for interrupts. */
 struct rte_intr_handle {
 	union {
@@ -63,7 +89,61 @@  struct rte_intr_handle {
 	uint32_t max_intr;               /**< max interrupt requested */
 	uint32_t nb_efd;                 /**< number of available efds */
 	int efds[RTE_MAX_RXTX_INTR_VEC_ID];  /**< intr vectors/efds mapping */
+	struct rte_epoll_event elist[RTE_MAX_RXTX_INTR_VEC_ID];
+					 /**< intr vector epoll event */
 	int *intr_vec;                   /**< intr vector number array */
 };
 
+#define RTE_EPOLL_PER_THREAD        -1  /**< to hint using per thread epfd */
+
+/**
+ * It waits for events on the epoll instance.
+ *
+ * @param epfd
+ *   Epoll instance fd on which the caller wait for events.
+ * @param events
+ *   Memory area contains the events that will be available for the caller.
+ * @param maxevents
+ *   Up to maxevents are returned, must greater than zero.
+ * @param timeout
+ *   Specifying a timeout of -1 causes a block indefinitely.
+ *   Specifying a timeout equal to zero cause to return immediately.
+ * @return
+ *   - On success, returns the number of available event.
+ *   - On failure, a negative value.
+ */
+int
+rte_epoll_wait(int epfd, struct rte_epoll_event *events,
+	       int maxevents, int timeout);
+
+/**
+ * It performs control operations on epoll instance referred by the epfd.
+ * It requests that the operation op be performed for the target fd.
+ *
+ * @param epfd
+ *   Epoll instance fd on which the caller perform control operations.
+ * @param op
+ *   The operation be performed for the target fd.
+ * @param fd
+ *   The target fd on which the control ops perform.
+ * @param event
+ *   Describes the object linked to the fd.
+ *   Note: The caller must take care the object deletion after CTL_DEL.
+ * @return
+ *   - On success, zero.
+ *   - On failure, a negative value.
+ */
+int
+rte_epoll_ctl(int epfd, int op, int fd,
+	      struct rte_epoll_event *event);
+
+/**
+ * The function returns the per thread epoll instance.
+ *
+ * @return
+ *   epfd the epoll instance referred to.
+ */
+int
+rte_intr_tls_epfd(void);
+
 #endif /* _RTE_LINUXAPP_INTERRUPTS_H_ */
diff --git a/lib/librte_eal/linuxapp/eal/rte_eal_version.map b/lib/librte_eal/linuxapp/eal/rte_eal_version.map
index 7e850a9..f388af6 100644
--- a/lib/librte_eal/linuxapp/eal/rte_eal_version.map
+++ b/lib/librte_eal/linuxapp/eal/rte_eal_version.map
@@ -98,3 +98,13 @@  DPDK_2.0 {
 
 	local: *;
 };
+
+DPDK_2.1 {
+	global:
+
+	rte_epoll_ctl;
+	rte_epoll_wait;
+	rte_intr_tls_epfd;
+
+	local: *;
+} DPDK_2.0;