[PATCH v2 6/8] lib/igt_drm_netlink: add event notify subscription and event wait support

Added event notification support with subscribe for an error-notify event
and wait for the event notification functionalities.

Signed-off-by: Ravi Kishore Koppuravuri <[email protected]>
---
v2:Handled SEQ_CHECK nl response using separate callback
   Added monotonic-clock deadline to wait for messages without exceeding the
   caller’s total timeout.
   Added support to receive events until it sees an event whose node ID and
   error ID match the requested values.
---
---
 lib/igt_drm_netlink.c | 159 +++++++++++++++++++++++++++++++++++++++++-
 lib/igt_drm_netlink.h |   6 ++
 2 files changed, 162 insertions(+), 3 deletions(-)

diff --git a/lib/igt_drm_netlink.c b/lib/igt_drm_netlink.c
index c32e10f2f..04f331b38 100644
--- a/lib/igt_drm_netlink.c
+++ b/lib/igt_drm_netlink.c
@@ -6,9 +6,11 @@
 #include <stdbool.h>
 #include <stdint.h>
 #include <errno.h>
+#include <poll.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <time.h>
 
 #include <netlink/errno.h>
 #include <netlink/genl/ctrl.h>
@@ -31,6 +33,27 @@ static int ras_command_cb(struct nl_msg *msg, void *arg)
 	switch (gnlh->cmd) {
 	case DRM_RAS_CMD_SET_ERROR_THRESHOLD:
 		break;
+	case DRM_RAS_CMD_ERROR_EVENT: {
+		struct nlattr *attrs[DRM_RAS_A_ERROR_EVENT_ATTRS_MAX + 1];
+
+		ret = genlmsg_parse(nlh, 0, attrs,
+				    DRM_RAS_A_ERROR_EVENT_ATTRS_MAX, NULL);
+		if (ret < 0)
+			return NL_SKIP;
+
+		if (!attrs[DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_ID] ||
+		    !attrs[DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_ID] ||
+		    !attrs[DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_VALUE])
+			return NL_SKIP;
+
+		ctx->event_node_id = nla_get_u32(attrs[DRM_RAS_A_ERROR_EVENT_ATTRS_NODE_ID]);
+		ctx->event_error_id = nla_get_u32(attrs[DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_ID]);
+		ctx->event_error_value =
+			nla_get_u32(attrs[DRM_RAS_A_ERROR_EVENT_ATTRS_ERROR_VALUE]);
+		ctx->event_received = ctx->event_node_id == ctx->node_id &&
+				      ctx->event_error_id == ctx->error_id;
+		break;
+	}
 	case DRM_RAS_CMD_GET_ERROR_COUNTER: {
 		struct nlattr *attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX + 1];
 
@@ -64,13 +87,20 @@ static int ras_command_cb(struct nl_msg *msg, void *arg)
 		return NL_SKIP;
 	}
 
-	ctx->reply_received = true;
-	if (ctx->ack_received)
-		ctx->cmd_done = true;
+	if (gnlh->cmd != DRM_RAS_CMD_ERROR_EVENT) {
+		ctx->reply_received = true;
+		if (ctx->ack_received)
+			ctx->cmd_done = true;
+	}
 
 	return NL_OK;
 }
 
+static int ras_multicast_seq_check_cb(struct nl_msg *msg, void *arg)
+{
+	return NL_OK;
+}
+
 static int ras_error_cb(struct sockaddr_nl *nla, struct nlmsgerr *err, void *arg)
 {
 	struct app_context *ctx = arg;
@@ -124,6 +154,23 @@ static int register_callbacks(struct nl_cb *cb, struct app_context *ctx)
 	return 0;
 }
 
+static int register_multicast_callbacks(struct nl_cb *cb,
+					struct app_context *ctx)
+{
+	int ret;
+
+	ret = nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, ras_command_cb, ctx);
+	if (ret < 0)
+		return ret;
+
+	ret = nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM,
+			ras_multicast_seq_check_cb, ctx);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int send_and_recv_nl_msg(struct app_context *ctx,
 				struct nl_cb *cb,
 				struct nl_msg *msg)
@@ -245,6 +292,10 @@ int init_app_context(struct app_context *ctx)
 	ctx->ack_received = false;
 	ctx->response_required = false;
 	ctx->error_threshold = 0;
+	ctx->event_node_id = UINT32_MAX;
+	ctx->event_error_id = UINT32_MAX;
+	ctx->event_error_value = 0;
+	ctx->event_received = false;
 	ctx->family_id = -1;
 
 	return 0;
@@ -265,6 +316,10 @@ void cleanup_app_context(struct app_context *ctx)
 	ctx->ack_received = false;
 	ctx->response_required = false;
 	ctx->error_threshold = 0;
+	ctx->event_node_id = UINT32_MAX;
+	ctx->event_error_id = UINT32_MAX;
+	ctx->event_error_value = 0;
+	ctx->event_received = false;
 	ctx->family_id = -1;
 }
 
@@ -410,3 +465,101 @@ int set_error_threshold(struct app_context *ctx)
 
 	return 0;
 }
+
+int subscribe_error_notify(struct app_context *ctx, const char *notify_group_name)
+{
+	int grp_id;
+	int ret;
+
+	if (!ctx || !ctx->sock || ctx->family_id < 0 ||
+	    !notify_group_name || notify_group_name[0] == '\0')
+		return -EINVAL;
+
+	grp_id = genl_ctrl_resolve_grp(ctx->sock,
+				       DRM_RAS_FAMILY_NAME,
+				       notify_group_name);
+	if (grp_id < 0)
+		return grp_id;
+
+	ret = nl_socket_add_membership(ctx->sock, grp_id);
+	if (ret < 0)
+		return ret;
+
+	igt_debug("Subscribed to DRM RAS multicast group '%s' (id=%d).\n",
+		  notify_group_name, grp_id);
+
+	return 0;
+}
+
+int wait_for_error_notify_event(struct app_context *ctx, int timeout_ms)
+{
+	struct nl_cb *cb;
+	struct pollfd pfd;
+	struct timespec start, now;
+	int remaining_ms;
+	int ret;
+
+	if (!ctx || !ctx->sock || ctx->family_id < 0)
+		return -EINVAL;
+
+	if (timeout_ms < -1)
+		return -EINVAL;
+
+	cb = nl_cb_alloc(NL_CB_DEFAULT);
+	if (!cb)
+		return -ENOMEM;
+
+	ret = register_multicast_callbacks(cb, ctx);
+	if (ret < 0) {
+		nl_cb_put(cb);
+		return ret;
+	}
+
+	ctx->event_received = false;
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	pfd.fd = nl_socket_get_fd(ctx->sock);
+	pfd.events = POLLIN;
+	pfd.revents = 0;
+
+	while (!ctx->event_received) {
+		if (timeout_ms == -1) {
+			remaining_ms = -1;
+		} else {
+			clock_gettime(CLOCK_MONOTONIC, &now);
+			remaining_ms = timeout_ms -
+				       (int)((now.tv_sec - start.tv_sec) * 1000 +
+				       (now.tv_nsec - start.tv_nsec) / 1000000);
+			if (remaining_ms <= 0) {
+				ret = -ETIMEDOUT;
+				break;
+			}
+		}
+
+		ret = poll(&pfd, 1, remaining_ms);
+		if (ret == 0) {
+			ret = -ETIMEDOUT;
+				break;
+		}
+
+		if (ret < 0) {
+			ret = -errno;
+			break;
+		}
+
+		ret = nl_recvmsgs(ctx->sock, cb);
+		if (ret < 0)
+			break;
+	}
+	nl_cb_put(cb);
+	if (ret < 0)
+		return ret;
+
+	if (!ctx->event_received)
+		return -ENOMSG;
+
+	igt_debug("Received error-notify event: node_id=%u error_id=%u value=%u\n",
+		  ctx->event_node_id, ctx->event_error_id, ctx->event_error_value);
+
+	return 0;
+}
diff --git a/lib/igt_drm_netlink.h b/lib/igt_drm_netlink.h
index 045dae403..cb7a05912 100644
--- a/lib/igt_drm_netlink.h
+++ b/lib/igt_drm_netlink.h
@@ -29,6 +29,10 @@ struct app_context {
 	bool ack_received;
 	bool response_required;
 	uint32_t error_threshold;
+	uint32_t event_node_id;
+	uint32_t event_error_id;
+	uint32_t event_error_value;
+	bool event_received;
 	int family_id;
 };
 
@@ -39,6 +43,8 @@ int init_nl_socket(struct app_context *ctx);
 int get_error_counter(struct app_context *ctx);
 int get_error_threshold(struct app_context *ctx);
 int set_error_threshold(struct app_context *ctx);
+int subscribe_error_notify(struct app_context *ctx, const char *notify_group_name);
+int wait_for_error_notify_event(struct app_context *ctx, int timeout_ms);
 
 #endif /* IGT_DRM_NETLINK_H */
 
-- 
2.34.1