net/mlx5: HWS, fix complex rules rehash error flow

Moving rules from matcher to matcher should not fail.
However, if it does fail due to various reasons, the error flow
should allow the kernel to continue functioning (albeit with broken
steering rules) instead of going into series of soft lock-ups or
some other problematic behaviour.

Similar to the simple rules, complex rules rehash logic suffers
from the same problems. This patch fixes the error flow for moving
complex rules:
 - If new rule creation fails before it was even enqeued, do not
   poll for completion
 - If TIMEOUT happened while moving the rule, no point trying
   to poll for completions for other rules. Something is broken,
   completion won't come, just abort the rehash sequence.
 - If some other completion with error received, don't give up.
   Continue handling rest of the rules to minimize the damage.
 - Make sure that the first error code that was received will
   be actually returned to the caller instead of replacing it
   with the generic error code.

All the aforementioned issues stem from the same bad error flow,
so no point fixing them one by one and leaving partially broken
code - fixing them in one patch.

Fixes: 17e0accac577 ("net/mlx5: HWS, support complex matchers")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250817202323.308604-4-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
index ca7501c5746886efceb40c637528b512729702b1..14e79579c719c287dc924c9e83a8c376516d6da1 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc_complex.c
@@ -1328,11 +1328,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
        struct mlx5hws_context *ctx = bwc_matcher->matcher->tbl->ctx;
        struct mlx5hws_matcher *matcher = bwc_matcher->matcher;
-       bool move_error = false, poll_error = false;
        u16 bwc_queues = mlx5hws_bwc_queues(ctx);
        struct mlx5hws_bwc_rule *tmp_bwc_rule;
        struct mlx5hws_rule_attr rule_attr;
        struct mlx5hws_table *isolated_tbl;
+       int move_error = 0, poll_error = 0;
        struct mlx5hws_rule *tmp_rule;
        struct list_head *rules_list;
        u32 expected_completions = 1;
@@ -1391,11 +1391,15 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
                        ret = mlx5hws_matcher_resize_rule_move(matcher,
                                                               tmp_rule,
                                                               &rule_attr);
-                       if (unlikely(ret && !move_error)) {
-                               mlx5hws_err(ctx,
-                                           "Moving complex BWC rule failed (%d), attempting to move rest of the rules\n",
-                                           ret);
-                               move_error = true;
+                       if (unlikely(ret)) {
+                               if (!move_error) {
+                                       mlx5hws_err(ctx,
+                                                   "Moving complex BWC rule: move failed (%d), attempting to move rest of the rules\n",
+                                                   ret);
+                                       move_error = ret;
+                               }
+                               /* Rule wasn't queued, no need to poll */
+                               continue;
                        }
 
                        expected_completions = 1;
@@ -1403,11 +1407,19 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
                                                     rule_attr.queue_id,
                                                     &expected_completions,
                                                     true);
-                       if (unlikely(ret && !poll_error)) {
-                               mlx5hws_err(ctx,
-                                           "Moving complex BWC rule: poll failed (%d), attempting to move rest of the rules\n",
-                                           ret);
-                               poll_error = true;
+                       if (unlikely(ret)) {
+                               if (ret == -ETIMEDOUT) {
+                                       mlx5hws_err(ctx,
+                                                   "Moving complex BWC rule: timeout polling for completions (%d), aborting rehash\n",
+                                                   ret);
+                                       return ret;
+                               }
+                               if (!poll_error) {
+                                       mlx5hws_err(ctx,
+                                                   "Moving complex BWC rule: polling for completions failed (%d), attempting to move rest of the rules\n",
+                                                   ret);
+                                       poll_error = ret;
+                               }
                        }
 
                        /* Done moving the rule to the new matcher,
@@ -1422,8 +1434,11 @@ mlx5hws_bwc_matcher_move_all_complex(struct mlx5hws_bwc_matcher *bwc_matcher)
                }
        }
 
-       if (move_error || poll_error)
-               ret = -EINVAL;
+       /* Return the first error that happened */
+       if (unlikely(move_error))
+               return move_error;
+       if (unlikely(poll_error))
+               return poll_error;
 
        return ret;
 }