[dpdk-dev] [PATCH v5 2/9] gpudev: add event notification

[<eagostini@nvidia.com>]

From: Thomas Monjalon <thomas@monjalon.net>

Callback functions may be registered for a device event.
Callback management is per-process and not thread-safe.

The events RTE_GPU_EVENT_NEW and RTE_GPU_EVENT_DEL
are notified respectively after creation and before removal
of a device, as part of the library functions.
Some future events may be emitted from drivers.

Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
---
 lib/gpudev/gpudev.c        | 148 +++++++++++++++++++++++++++++++++++++
 lib/gpudev/gpudev_driver.h |   7 ++
 lib/gpudev/rte_gpudev.h    |  70 ++++++++++++++++++
 lib/gpudev/version.map     |   3 +
 4 files changed, 228 insertions(+)

diff --git a/lib/gpudev/gpudev.c b/lib/gpudev/gpudev.c
index aeb021f2cc..07572ae040 100644
--- a/lib/gpudev/gpudev.c
+++ b/lib/gpudev/gpudev.c
@@ -3,6 +3,7 @@
  */
 
 #include <rte_eal.h>
+#include <rte_tailq.h>
 #include <rte_string_fns.h>
 #include <rte_errno.h>
 #include <rte_log.h>
@@ -27,6 +28,16 @@ static int16_t gpu_max;
 /* Number of currently valid devices */
 static int16_t gpu_count;
 
+/* Event callback object */
+struct rte_gpu_callback {
+	TAILQ_ENTRY(rte_gpu_callback) next;
+	rte_gpu_callback_t *function;
+	void *user_data;
+	enum rte_gpu_event event;
+};
+static rte_rwlock_t gpu_callback_lock = RTE_RWLOCK_INITIALIZER;
+static void gpu_free_callbacks(struct rte_gpu *dev);
+
 int
 rte_gpu_init(size_t dev_max)
 {
@@ -166,6 +177,7 @@ rte_gpu_allocate(const char *name)
 	dev->info.name = dev->name;
 	dev->info.dev_id = dev_id;
 	dev->info.numa_node = -1;
+	TAILQ_INIT(&dev->callbacks);
 
 	gpu_count++;
 	GPU_LOG(DEBUG, "new device %s (id %d) of total %d",
@@ -180,6 +192,8 @@ rte_gpu_complete_new(struct rte_gpu *dev)
 		return;
 
 	dev->state = RTE_GPU_STATE_INITIALIZED;
+	dev->state = RTE_GPU_STATE_INITIALIZED;
+	rte_gpu_notify(dev, RTE_GPU_EVENT_NEW);
 }
 
 int
@@ -192,6 +206,9 @@ rte_gpu_release(struct rte_gpu *dev)
 
 	GPU_LOG(DEBUG, "free device %s (id %d)",
 			dev->info.name, dev->info.dev_id);
+	rte_gpu_notify(dev, RTE_GPU_EVENT_DEL);
+
+	gpu_free_callbacks(dev);
 	dev->state = RTE_GPU_STATE_UNUSED;
 	gpu_count--;
 
@@ -224,6 +241,137 @@ rte_gpu_close(int16_t dev_id)
 	return firsterr;
 }
 
+int
+rte_gpu_callback_register(int16_t dev_id, enum rte_gpu_event event,
+		rte_gpu_callback_t *function, void *user_data)
+{
+	int16_t next_dev, last_dev;
+	struct rte_gpu_callback_list *callbacks;
+	struct rte_gpu_callback *callback;
+
+	if (!rte_gpu_is_valid(dev_id) && dev_id != RTE_GPU_ID_ANY) {
+		GPU_LOG(ERR, "register callback of invalid ID %d", dev_id);
+		rte_errno = ENODEV;
+		return -rte_errno;
+	}
+	if (function == NULL) {
+		GPU_LOG(ERR, "cannot register callback without function");
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+
+	if (dev_id == RTE_GPU_ID_ANY) {
+		next_dev = 0;
+		last_dev = gpu_max - 1;
+	} else {
+		next_dev = last_dev = dev_id;
+	}
+
+	rte_rwlock_write_lock(&gpu_callback_lock);
+	do {
+		callbacks = &gpus[next_dev].callbacks;
+
+		/* check if not already registered */
+		TAILQ_FOREACH(callback, callbacks, next) {
+			if (callback->event == event &&
+					callback->function == function &&
+					callback->user_data == user_data) {
+				GPU_LOG(INFO, "callback already registered");
+				return 0;
+			}
+		}
+
+		callback = malloc(sizeof(*callback));
+		if (callback == NULL) {
+			GPU_LOG(ERR, "cannot allocate callback");
+			return -ENOMEM;
+		}
+		callback->function = function;
+		callback->user_data = user_data;
+		callback->event = event;
+		TAILQ_INSERT_TAIL(callbacks, callback, next);
+
+	} while (++next_dev <= last_dev);
+	rte_rwlock_write_unlock(&gpu_callback_lock);
+
+	return 0;
+}
+
+int
+rte_gpu_callback_unregister(int16_t dev_id, enum rte_gpu_event event,
+		rte_gpu_callback_t *function, void *user_data)
+{
+	int16_t next_dev, last_dev;
+	struct rte_gpu_callback_list *callbacks;
+	struct rte_gpu_callback *callback, *nextcb;
+
+	if (!rte_gpu_is_valid(dev_id) && dev_id != RTE_GPU_ID_ANY) {
+		GPU_LOG(ERR, "unregister callback of invalid ID %d", dev_id);
+		rte_errno = ENODEV;
+		return -rte_errno;
+	}
+	if (function == NULL) {
+		GPU_LOG(ERR, "cannot unregister callback without function");
+		rte_errno = EINVAL;
+		return -rte_errno;
+	}
+
+	if (dev_id == RTE_GPU_ID_ANY) {
+		next_dev = 0;
+		last_dev = gpu_max - 1;
+	} else {
+		next_dev = last_dev = dev_id;
+	}
+
+	rte_rwlock_write_lock(&gpu_callback_lock);
+	do {
+		callbacks = &gpus[next_dev].callbacks;
+		RTE_TAILQ_FOREACH_SAFE(callback, callbacks, next, nextcb) {
+			if (callback->event != event ||
+					callback->function != function ||
+					(callback->user_data != user_data &&
+					user_data != (void *)-1))
+				continue;
+			TAILQ_REMOVE(callbacks, callback, next);
+			free(callback);
+		}
+	} while (++next_dev <= last_dev);
+	rte_rwlock_write_unlock(&gpu_callback_lock);
+
+	return 0;
+}
+
+static void
+gpu_free_callbacks(struct rte_gpu *dev)
+{
+	struct rte_gpu_callback_list *callbacks;
+	struct rte_gpu_callback *callback, *nextcb;
+
+	callbacks = &dev->callbacks;
+	rte_rwlock_write_lock(&gpu_callback_lock);
+	RTE_TAILQ_FOREACH_SAFE(callback, callbacks, next, nextcb) {
+		TAILQ_REMOVE(callbacks, callback, next);
+		free(callback);
+	}
+	rte_rwlock_write_unlock(&gpu_callback_lock);
+}
+
+void
+rte_gpu_notify(struct rte_gpu *dev, enum rte_gpu_event event)
+{
+	int16_t dev_id;
+	struct rte_gpu_callback *callback;
+
+	dev_id = dev->info.dev_id;
+	rte_rwlock_read_lock(&gpu_callback_lock);
+	TAILQ_FOREACH(callback, &dev->callbacks, next) {
+		if (callback->event != event || callback->function == NULL)
+			continue;
+		callback->function(dev_id, event, callback->user_data);
+	}
+	rte_rwlock_read_unlock(&gpu_callback_lock);
+}
+
 int
 rte_gpu_info_get(int16_t dev_id, struct rte_gpu_info *info)
 {
diff --git a/lib/gpudev/gpudev_driver.h b/lib/gpudev/gpudev_driver.h
index 9e096e3b64..2a7089aa52 100644
--- a/lib/gpudev/gpudev_driver.h
+++ b/lib/gpudev/gpudev_driver.h
@@ -12,6 +12,7 @@
 #define RTE_GPUDEV_DRIVER_H
 
 #include <stdint.h>
+#include <sys/queue.h>
 
 #include <rte_dev.h>
 
@@ -43,6 +44,8 @@ struct rte_gpu {
 	struct rte_gpu_info info;
 	/* Driver functions. */
 	struct rte_gpu_ops ops;
+	/* Event callback list. */
+	TAILQ_HEAD(rte_gpu_callback_list, rte_gpu_callback) callbacks;
 	/* Current state (used or not) in the running process. */
 	enum rte_gpu_state state; /* Updated by this library. */
 	/* Driver-specific private data for the running process. */
@@ -64,4 +67,8 @@ void rte_gpu_complete_new(struct rte_gpu *dev);
 __rte_internal
 int rte_gpu_release(struct rte_gpu *dev);
 
+/* Call registered callbacks. No multi-process event. */
+__rte_internal
+void rte_gpu_notify(struct rte_gpu *dev, enum rte_gpu_event);
+
 #endif /* RTE_GPUDEV_DRIVER_H */
diff --git a/lib/gpudev/rte_gpudev.h b/lib/gpudev/rte_gpudev.h
index eb7cfa8c59..e1702fbfe4 100644
--- a/lib/gpudev/rte_gpudev.h
+++ b/lib/gpudev/rte_gpudev.h
@@ -31,6 +31,11 @@ extern "C" {
 
 /** Empty device ID. */
 #define RTE_GPU_ID_NONE -1
+/** Catch-all device ID. */
+#define RTE_GPU_ID_ANY INT16_MIN
+
+/** Catch-all callback data. */
+#define RTE_GPU_CALLBACK_ANY_DATA ((void *)-1)
 
 /** Store device info. */
 struct rte_gpu_info {
@@ -46,6 +51,18 @@ struct rte_gpu_info {
 	int16_t numa_node;
 };
 
+/** Flags passed in notification callback. */
+enum rte_gpu_event {
+	/** Device is just initialized. */
+	RTE_GPU_EVENT_NEW,
+	/** Device is going to be released. */
+	RTE_GPU_EVENT_DEL,
+};
+
+/** Prototype of event callback function. */
+typedef void (rte_gpu_callback_t)(int16_t dev_id,
+		enum rte_gpu_event event, void *user_data);
+
 /**
  * @warning
  * @b EXPERIMENTAL: this API may change without prior notice.
@@ -141,6 +158,59 @@ int16_t rte_gpu_find_next(int16_t dev_id);
 __rte_experimental
 int rte_gpu_close(int16_t dev_id);
 
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Register a function as event callback.
+ * A function may be registered multiple times for different events.
+ *
+ * @param dev_id
+ *   Device ID to get notified about.
+ *   RTE_GPU_ID_ANY means all devices.
+ * @param event
+ *   Device event to be registered for.
+ * @param function
+ *   Callback function to be called on event.
+ * @param user_data
+ *   Optional parameter passed in the callback.
+ *
+ * @return
+ *   0 on success, -rte_errno otherwise:
+ *   - ENODEV if invalid dev_id
+ *   - EINVAL if NULL function
+ *   - ENOMEM if out of memory
+ */
+__rte_experimental
+int rte_gpu_callback_register(int16_t dev_id, enum rte_gpu_event event,
+		rte_gpu_callback_t *function, void *user_data);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Unregister for an event.
+ *
+ * @param dev_id
+ *   Device ID to be silenced.
+ *   RTE_GPU_ID_ANY means all devices.
+ * @param event
+ *   Registered event.
+ * @param function
+ *   Registered function.
+ * @param user_data
+ *   Optional parameter as registered.
+ *   RTE_GPU_CALLBACK_ANY_DATA is a catch-all.
+ *
+ * @return
+ *   0 on success, -rte_errno otherwise:
+ *   - ENODEV if invalid dev_id
+ *   - EINVAL if NULL function
+ */
+__rte_experimental
+int rte_gpu_callback_unregister(int16_t dev_id, enum rte_gpu_event event,
+		rte_gpu_callback_t *function, void *user_data);
+
 /**
  * @warning
  * @b EXPERIMENTAL: this API may change without prior notice.
diff --git a/lib/gpudev/version.map b/lib/gpudev/version.map
index 6ac6b327e2..b3b6b76c1c 100644
--- a/lib/gpudev/version.map
+++ b/lib/gpudev/version.map
@@ -2,6 +2,8 @@ EXPERIMENTAL {
 	global:
 
 	# added in 21.11
+	rte_gpu_callback_register;
+	rte_gpu_callback_unregister;
 	rte_gpu_close;
 	rte_gpu_count_avail;
 	rte_gpu_find_next;
@@ -16,5 +18,6 @@ INTERNAL {
 	rte_gpu_allocate;
 	rte_gpu_complete_new;
 	rte_gpu_get_by_name;
+	rte_gpu_notify;
 	rte_gpu_release;
 };
-- 
2.17.1