devlink: Fix reporter's recovery condition

BugLink: https://bugs.launchpad.net/bugs/1900624
[ Upstream commit bea0c5c942d3b4e9fb6ed45f6a7de74c6b112437 ]

Devlink health core conditions the reporter's recovery with the
expiration of the grace period. This is not relevant for the first
recovery. Explicitly demand that the grace period will only apply to
recoveries other than the first.

Fixes: c8e1da0bf923 ("devlink: Add health report functionality")
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>
Signed-off-by: Ian May <ian.may@canonical.com>

diff --git a/net/core/devlink.c b/net/core/devlink.c
index 07ac74e877745b61090d4684d8658cddfcf9d6ec..ed592f86bacb7520e2269a34bc983de0e3e08dea 100644 (file)
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4828,6 +4828,7 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
 {
        enum devlink_health_reporter_state prev_health_state;
        struct devlink *devlink = reporter->devlink;
+       unsigned long recover_ts_threshold;
 
        /* write a log message of the current error */
        WARN_ON(!msg);
@@ -4837,10 +4838,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter,
        reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR;
 
        /* abort if the previous error wasn't recovered */
+       recover_ts_threshold = reporter->last_recovery_ts +
+                              msecs_to_jiffies(reporter->graceful_period);
        if (reporter->auto_recover &&
            (prev_health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY ||
-            jiffies - reporter->last_recovery_ts <
-            msecs_to_jiffies(reporter->graceful_period))) {
+            (reporter->last_recovery_ts && reporter->recovery_count &&
+             time_is_after_jiffies(recover_ts_threshold)))) {
                trace_devlink_health_recover_aborted(devlink,
                                                     reporter->ops->name,
                                                     reporter->health_state,