[Intel-gfx] [PATCH i-g-t v4 08/20] tests/core_hotunplug: Handle device close errors

[Janusz Krzysztofik]

The test now ignores device close errors.  Those errors are believed to
have no influence on device health so there is no need to process them
the same way as we mostly do on errors, i.e., notify CI about a problem
via igt_abort.  However, those errors may indicate issues with the test
itself.  Moreover, impact of those errors on operations performed by
subtests, like driver unbind or device remove, should be perceived as
undefined.  Then, we should fail as soon as a device or device sysfs
node close error occurs in a subtest and also skip subsequent subtests.
However, once a driver unbind or device unplug operation has been
attempted by a subtest, we would still like to check the device health.

When in a subtest, store results of device close operations for future
reference.  Reuse file descriptor fields of the hotunplug structure for
that.  Unless in between of a driver remove or device unplug operation
and a successful device health check completion, fail current test
section right after a device close error occurs, warn otherwise.  If
still running, examine device file descriptor fields in subsequent
igt_fixture sections and skip on errors.

v2: Fix a typo in post_healthcheck function name.
v3: Don't fail on close error after successful health check, warn only,
  - move duplicated messages to helpers.

Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik at linux.intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski at intel.com> # v1
---
 tests/core_hotunplug.c | 64 +++++++++++++++++++++++++++++++++---------
 1 file changed, 50 insertions(+), 14 deletions(-)

diff --git a/tests/core_hotunplug.c b/tests/core_hotunplug.c
index 4f7e89c95..f7a54010b 100644
--- a/tests/core_hotunplug.c
+++ b/tests/core_hotunplug.c
@@ -43,7 +43,7 @@ struct hotunplug {
 		int sysfs_dev;
 		int sysfs_bus;
 		int sysfs_drv;
-	} fd;
+	} fd;	/* >= 0: valid fd, == -1: closed, < -1: close failed */
 	const char *dev_bus_addr;
 	const char *failure;
 };
@@ -67,6 +67,25 @@ static int local_drm_open_driver(const char *prefix, const char *suffix)
 	return fd_drm;
 }
 
+static int local_close(int fd, const char *message)
+{
+	errno = 0;
+	if (igt_warn_on_f(close(fd), "%s\n", message))
+		return -errno;	/* (never -1) */
+
+	return -1;	/* success - return 'closed' */
+}
+
+static int close_device(int fd_drm)
+{
+	return local_close(fd_drm, "Device close failed");
+}
+
+static int close_sysfs(int fd_sysfs_dev)
+{
+	return local_close(fd_sysfs_dev, "Device sysfs node close failed");
+}
+
 static void prepare_for_unbind(struct hotunplug *priv, char *buf, int buflen)
 {
 	int len;
@@ -83,7 +102,8 @@ static void prepare_for_unbind(struct hotunplug *priv, char *buf, int buflen)
 	igt_assert(priv->dev_bus_addr++);
 
 	/* sysfs_dev no longer needed */
-	close(priv->fd.sysfs_dev);
+	priv->fd.sysfs_dev = close_sysfs(priv->fd.sysfs_dev);
+	igt_assert_eq(priv->fd.sysfs_dev, -1);
 }
 
 static void prepare(struct hotunplug *priv, char *buf, int buflen)
@@ -142,7 +162,7 @@ static void device_unplug(struct hotunplug *priv, const char *prefix)
 	igt_reset_timeout();
 	priv->failure = NULL;
 
-	close(priv->fd.sysfs_dev);
+	priv->fd.sysfs_dev = close_sysfs(priv->fd.sysfs_dev);
 }
 
 /* Re-discover the device by rescanning its bus */
@@ -161,6 +181,7 @@ static void bus_rescan(struct hotunplug *priv)
 
 static void healthcheck(struct hotunplug *priv)
 {
+	/* preserve error code potentially stored before in priv->fd.drm */
 	int fd_drm;
 
 	/* device name may have changed, rebuild IGT device list */
@@ -176,7 +197,17 @@ static void healthcheck(struct hotunplug *priv)
 		priv->failure = NULL;
 	}
 
-	close(fd_drm);
+	fd_drm = close_device(fd_drm);
+	if (priv->fd.drm == -1)	/* store result if no error code to preserve */
+		priv->fd.drm = fd_drm;
+}
+
+static void post_healthcheck(struct hotunplug *priv)
+{
+	igt_abort_on_f(priv->failure, "%s\n", priv->failure);
+
+	igt_require(priv->fd.drm == -1);
+	igt_require(priv->fd.sysfs_dev == -1);
 }
 
 static void set_filter_from_device(int fd)
@@ -203,7 +234,8 @@ static void unbind_rebind(struct hotunplug *priv)
 	prepare(priv, buf, sizeof(buf));
 
 	igt_debug("closing the device\n");
-	close(priv->fd.drm);
+	priv->fd.drm = close_device(priv->fd.drm);
+	igt_assert_eq(priv->fd.drm, -1);
 
 	driver_unbind(priv, "");
 
@@ -217,7 +249,8 @@ static void unplug_rescan(struct hotunplug *priv)
 	prepare(priv, NULL, 0);
 
 	igt_debug("closing the device\n");
-	close(priv->fd.drm);
+	priv->fd.drm = close_device(priv->fd.drm);
+	igt_assert_eq(priv->fd.drm, -1);
 
 	device_unplug(priv, "");
 
@@ -237,7 +270,7 @@ static void hotunbind_lateclose(struct hotunplug *priv)
 	driver_bind(priv);
 
 	igt_debug("late closing the unbound device instance\n");
-	close(priv->fd.drm);
+	priv->fd.drm = close_device(priv->fd.drm);
 
 	healthcheck(priv);
 }
@@ -251,7 +284,7 @@ static void hotunplug_lateclose(struct hotunplug *priv)
 	bus_rescan(priv);
 
 	igt_debug("late closing the removed device instance\n");
-	close(priv->fd.drm);
+	priv->fd.drm = close_device(priv->fd.drm);
 
 	healthcheck(priv);
 }
@@ -260,7 +293,10 @@ static void hotunplug_lateclose(struct hotunplug *priv)
 
 igt_main
 {
-	struct hotunplug priv = { .failure = NULL, };
+	struct hotunplug priv = {
+		.fd		= { .drm = -1, .sysfs_dev = -1, },
+		.failure	= NULL,
+	};
 
 	igt_fixture {
 		int fd_drm;
@@ -276,7 +312,7 @@ igt_main
 		/* Make sure subtests always reopen the same device */
 		set_filter_from_device(fd_drm);
 
-		close(fd_drm);
+		igt_assert_eq(close_device(fd_drm), -1);
 	}
 
 	igt_describe("Check if the driver can be cleanly unbound from a device believed to be closed");
@@ -284,26 +320,26 @@ igt_main
 		unbind_rebind(&priv);
 
 	igt_fixture
-		igt_abort_on_f(priv.failure, "%s\n", priv.failure);
+		post_healthcheck(&priv);
 
 	igt_describe("Check if a device believed to be closed can be cleanly unplugged");
 	igt_subtest("unplug-rescan")
 		unplug_rescan(&priv);
 
 	igt_fixture
-		igt_abort_on_f(priv.failure, "%s\n", priv.failure);
+		post_healthcheck(&priv);
 
 	igt_describe("Check if the driver can be cleanly unbound from a still open device, then released");
 	igt_subtest("hotunbind-lateclose")
 		hotunbind_lateclose(&priv);
 
 	igt_fixture
-		igt_abort_on_f(priv.failure, "%s\n", priv.failure);
+		post_healthcheck(&priv);
 
 	igt_describe("Check if a still open device can be cleanly unplugged, then released");
 	igt_subtest("hotunplug-lateclose")
 		hotunplug_lateclose(&priv);
 
 	igt_fixture
-		igt_abort_on_f(priv.failure, "%s\n", priv.failure);
+		post_healthcheck(&priv);
 }
-- 
2.21.1