Add linux events

This topic branch leverages the Solaris style FMA call points
in ZFS to create a user space visible event notification system
under Linux.  This new system is called zevent and it unifies
all previous Solaris style ereports and sysevent notifications.

Under this Linux specific scheme when a sysevent or ereport event
occurs an nvlist describing the event is created which looks almost
exactly like a Solaris ereport.  These events are queued up in the
kernel when they occur and conditionally logged to the console.
It is then up to a user space application to consume the events
and do whatever it likes with them.

To make this possible the existing /dev/zfs ABI has been extended
with two new ioctls which behave as follows.

* ZFS_IOC_EVENTS_NEXT
Get the next pending event.  The kernel will keep track of the last
event consumed by the file descriptor and provide the next one if
available.  If no new events are available the ioctl() will block
waiting for the next event.  This ioctl may also be called in a
non-blocking mode by setting zc.zc_guid = ZEVENT_NONBLOCK.  In the
non-blocking case if no events are available ENOENT will be returned.
It is possible that ESHUTDOWN will be returned if the ioctl() is
called while module unloading is in progress.  And finally ENOMEM
may occur if the provided nvlist buffer is not large enough to
contain the entire event.

* ZFS_IOC_EVENTS_CLEAR
Clear are events queued by the kernel.  The kernel will keep a fairly
large number of recent events queued, use this ioctl to clear the
in kernel list.  This will effect all user space processes consuming
events.

The zpool command has been extended to use this events ABI with the
'events' subcommand.  You may run 'zpool events -v' to output a
verbose log of all recent events.  This is very similar to the
Solaris 'fmdump -ev' command with the key difference being it also
includes what would be considered sysevents under Solaris.  You
may also run in follow mode with the '-f' option.  To clear the
in kernel event queue use the '-c' option.

$ sudo cmd/zpool/zpool events -fv
TIME                        CLASS
May 13 2010 16:31:15.777711000 ereport.fs.zfs.config.sync
        class = "ereport.fs.zfs.config.sync"
        ena = 0x40982b7897700001
        detector = (embedded nvlist)
                version = 0x0
                scheme = "zfs"
                pool = 0xed976600de75dfa6
        (end detector)

        time = 0x4bec8bc3 0x2e5aed98
        pool = "zpios"
        pool_guid = 0xed976600de75dfa6
        pool_context = 0x0

While the 'zpool events' command is handy for interactive debugging
it is not expected to be the primary consumer of zevents.  This ABI
was primarily added to facilitate the addition of a user space
monitoring daemon.  This daemon would consume all events posted by
the kernel and based on the type of event perform an action.  For
most events simply forwarding them on to syslog is likely enough.
But this interface also cleanly allows for more sophisticated
actions to be taken such as generating an email for a failed drive.

Signed-off-by: Brian Behlendorf <[email protected]>

3 files changed, 91 insertions, 3 deletions

diff --git a/lib/libzfs/include/libzfs.h b/lib/libzfs/include/libzfs.h
index ea34cc9ef..b0287ed1f 100644
--- a/lib/libzfs/include/libzfs.h
+++ b/lib/libzfs/include/libzfs.h
@@ -368,6 +368,8 @@ extern int zpool_history_unpack(char *, uint64_t, uint64_t *,
 extern void zpool_set_history_str(const char *subcommand, int argc,
     char **argv, char *history_str);
 extern int zpool_stage_history(libzfs_handle_t *, const char *);
+extern int zpool_events_next(libzfs_handle_t *, nvlist_t **, int *, int, int);
+extern int zpool_events_clear(libzfs_handle_t *, int *);
 extern void zpool_obj_to_path(zpool_handle_t *, uint64_t, uint64_t, char *,
     size_t len);
 extern int zfs_ioctl(libzfs_handle_t *, int, struct zfs_cmd *);
diff --git a/lib/libzfs/libzfs_pool.c b/lib/libzfs/libzfs_pool.c
index f1edb77f0..42f303894 100644
--- a/lib/libzfs/libzfs_pool.c
+++ b/lib/libzfs/libzfs_pool.c
@@ -3474,6 +3474,94 @@ zpool_get_history(zpool_handle_t *zhp, nvlist_t **nvhisp)
 	return (err);
 }
 
+/*
+ * Retrieve the next event.  If there is a new event available 'nvp' will
+ * contain a newly allocated nvlist and 'dropped' will be set to the number
+ * of missed events since the last call to this function.  When 'nvp' is
+ * set to NULL it indicates no new events are available.  In either case
+ * the function returns 0 and it is up to the caller to free 'nvp'.  In
+ * the case of a fatal error the function will return a non-zero value.
+ * When the function is called in blocking mode it will not return until
+ * a new event is available.
+ */
+int
+zpool_events_next(libzfs_handle_t *hdl, nvlist_t **nvp,
+    int *dropped, int block, int cleanup_fd)
+{
+	zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 0 };
+	int error = 0;
+
+	*nvp = NULL;
+	*dropped = 0;
+	zc.zc_cleanup_fd = cleanup_fd;
+
+	if (!block)
+		zc.zc_guid = ZEVENT_NONBLOCK;
+
+	if (zcmd_alloc_dst_nvlist(hdl, &zc, ZEVENT_SIZE) != 0)
+		return (-1);
+
+retry:
+	if (zfs_ioctl(hdl, ZFS_IOC_EVENTS_NEXT, &zc) != 0) {
+		switch (errno) {
+		case ESHUTDOWN:
+			error = zfs_error_fmt(hdl, EZFS_POOLUNAVAIL,
+			    dgettext(TEXT_DOMAIN, "zfs shutdown"));
+			goto out;
+		case ENOENT:
+			/* Blocking error case should not occur */
+			if (block)
+				error = zpool_standard_error_fmt(hdl, errno,
+				    dgettext(TEXT_DOMAIN, "cannot get event"));
+
+			goto out;
+		case ENOMEM:
+			if (zcmd_expand_dst_nvlist(hdl, &zc) != 0) {
+				error = zfs_error_fmt(hdl, EZFS_NOMEM,
+				    dgettext(TEXT_DOMAIN, "cannot get event"));
+				goto out;
+			} else {
+				goto retry;
+			}
+		default:
+			error = zpool_standard_error_fmt(hdl, errno,
+			    dgettext(TEXT_DOMAIN, "cannot get event"));
+			goto out;
+		}
+	}
+
+	error = zcmd_read_dst_nvlist(hdl, &zc, nvp);
+	if (error != 0)
+		goto out;
+
+	*dropped = (int)zc.zc_cookie;
+out:
+	zcmd_free_nvlists(&zc);
+
+	return (error);
+}
+
+/*
+ * Clear all events.
+ */
+int
+zpool_events_clear(libzfs_handle_t *hdl, int *count)
+{
+	zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 0 };
+	char msg[1024];
+
+	(void) snprintf(msg, sizeof (msg), dgettext(TEXT_DOMAIN,
+	    "cannot clear events"));
+
+	if (zfs_ioctl(hdl, ZFS_IOC_EVENTS_CLEAR, &zc) != 0)
+		return (zpool_standard_error_fmt(hdl, errno, msg));
+
+	if (count != NULL)
+		*count = (int)zc.zc_cookie; /* # of events cleared */
+
+	return (0);
+}
+
 void
 zpool_obj_to_path(zpool_handle_t *zhp, uint64_t dsobj, uint64_t obj,
     char *pathname, size_t len)
diff --git a/lib/libzpool/include/sys/zfs_context.h b/lib/libzpool/include/sys/zfs_context.h
index f2776566c..34c351bd0 100644
--- a/lib/libzpool/include/sys/zfs_context.h
+++ b/lib/libzpool/include/sys/zfs_context.h
@@ -57,7 +57,6 @@ extern "C" {
 #include <atomic.h>
 #include <dirent.h>
 #include <time.h>
-#include <libsysevent.h>
 #include <sys/note.h>
 #include <sys/types.h>
 #include <sys/cred.h>
@@ -71,8 +70,7 @@ extern "C" {
 #include <sys/sdt.h>
 #include <sys/kstat.h>
 #include <sys/u8_textprep.h>
-#include <sys/sysevent/eventdefs.h>
-#include <sys/sysevent/dev.h>
+#include <sys/fm/fs/zfs.h>
 #include <sys/sunddi.h>
 
 /*