RDMA/efa: Properly handle unexpected AQ completions

Do not try to handle admin command completion if it has an unexpected
command id and print a relevant error message.

Reviewed-by: Firas Jahjah <firasj@amazon.com>
Reviewed-by: Yehuda Yitschak <yehuday@amazon.com>
Signed-off-by: Michael Margolin <mrgolin@amazon.com>
Link: https://lore.kernel.org/r/20240513064630.6247-1-mrgolin@amazon.com
Reviewed-by: Gal Pressman <gal.pressman@linux.dev>
Signed-off-by: Leon Romanovsky <leon@kernel.org>

diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c
index 16a24a05fc2a60da16723b7fb29ea7e02c4e6aef..bafd210dd43e86087160e1715c50709b6006e0a9 100644 (file)
--- a/drivers/infiniband/hw/efa/efa_com.c
+++ b/drivers/infiniband/hw/efa/efa_com.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
 /*
- * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #include "efa_com.h"
@@ -406,8 +406,8 @@ static struct efa_comp_ctx *efa_com_submit_admin_cmd(struct efa_com_admin_queue
        return comp_ctx;
 }
 
-static void efa_com_handle_single_admin_completion(struct efa_com_admin_queue *aq,
-                                                  struct efa_admin_acq_entry *cqe)
+static int efa_com_handle_single_admin_completion(struct efa_com_admin_queue *aq,
+                                                 struct efa_admin_acq_entry *cqe)
 {
        struct efa_comp_ctx *comp_ctx;
        u16 cmd_id;
@@ -416,11 +416,11 @@ static void efa_com_handle_single_admin_completion(struct efa_com_admin_queue *a
                         EFA_ADMIN_ACQ_COMMON_DESC_COMMAND_ID);
 
        comp_ctx = efa_com_get_comp_ctx(aq, cmd_id, false);
-       if (!comp_ctx) {
+       if (comp_ctx->status != EFA_CMD_SUBMITTED) {
                ibdev_err(aq->efa_dev,
-                         "comp_ctx is NULL. Changing the admin queue running state\n");
-               clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
-               return;
+                         "Received completion with unexpected command id[%d], sq producer: %d, sq consumer: %d, cq consumer: %d\n",
+                         cmd_id, aq->sq.pc, aq->sq.cc, aq->cq.cc);
+               return -EINVAL;
        }
 
        comp_ctx->status = EFA_CMD_COMPLETED;
@@ -428,14 +428,17 @@ static void efa_com_handle_single_admin_completion(struct efa_com_admin_queue *a
 
        if (!test_bit(EFA_AQ_STATE_POLLING_BIT, &aq->state))
                complete(&comp_ctx->wait_event);
+
+       return 0;
 }
 
 static void efa_com_handle_admin_completion(struct efa_com_admin_queue *aq)
 {
        struct efa_admin_acq_entry *cqe;
        u16 queue_size_mask;
-       u16 comp_num = 0;
+       u16 comp_cmds = 0;
        u8 phase;
+       int err;
        u16 ci;
 
        queue_size_mask = aq->depth - 1;
@@ -453,10 +456,12 @@ static void efa_com_handle_admin_completion(struct efa_com_admin_queue *aq)
                 * phase bit was validated
                 */
                dma_rmb();
-               efa_com_handle_single_admin_completion(aq, cqe);
+               err = efa_com_handle_single_admin_completion(aq, cqe);
+               if (!err)
+                       comp_cmds++;
 
+               aq->cq.cc++;
                ci++;
-               comp_num++;
                if (ci == aq->depth) {
                        ci = 0;
                        phase = !phase;
@@ -465,10 +470,9 @@ static void efa_com_handle_admin_completion(struct efa_com_admin_queue *aq)
                cqe = &aq->cq.entries[ci];
        }
 
-       aq->cq.cc += comp_num;
        aq->cq.phase = phase;
-       aq->sq.cc += comp_num;
-       atomic64_add(comp_num, &aq->stats.completed_cmd);
+       aq->sq.cc += comp_cmds;
+       atomic64_add(comp_cmds, &aq->stats.completed_cmd);
 }
 
 static int efa_com_comp_status_to_errno(u8 comp_status)