summaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
diff options
context:
space:
mode:
authorKashyap Desai <kashyap.desai@broadcom.com>2023-06-16 09:17:00 +0300
committerJason Gunthorpe <jgg@nvidia.com>2023-06-26 15:44:07 +0300
commit25ed2d409f5ff73f1bde8e9b2863f686364cbc7f (patch)
treedf8707642cb58ab4e78f56e1f90b50d089844970 /drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
parentc8dce4e7438be24be7a5b8477555ba03c0fb16ae (diff)
downloadlinux-25ed2d409f5ff73f1bde8e9b2863f686364cbc7f.tar.xz
RDMA/bnxt_re: Refactor code around bnxt_qplib_map_rc()
Update function comment of bnxt_qplib_map_rc() Remove intermediate return value ENXIO and directly called bnxt_qplib_map_rc() from __send_message_basic_sanity(). Link: https://lore.kernel.org/r/20230616061700.741769-2-kashyap.desai@broadcom.com Reported-by: Dan Carpenter <dan.carpenter@linaro.org> Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com> Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Diffstat (limited to 'drivers/infiniband/hw/bnxt_re/qplib_rcfw.c')
-rw-r--r--drivers/infiniband/hw/bnxt_re/qplib_rcfw.c23
1 files changed, 15 insertions, 8 deletions
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 1aa7c7b9ddb1..b30e66b64827 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -57,13 +57,20 @@ static void bnxt_qplib_service_creq(struct tasklet_struct *t);
* bnxt_qplib_map_rc - map return type based on opcode
* @opcode - roce slow path opcode
*
- * In some cases like firmware halt is detected, the driver is supposed to
- * remap the error code of the timed out command.
+ * case #1
+ * Firmware initiated error recovery is a safe state machine and
+ * driver can consider all the underlying rdma resources are free.
+ * In this state, it is safe to return success for opcodes related to
+ * destroying rdma resources (like destroy qp, destroy cq etc.).
*
- * It is not safe to assume hardware is really inactive so certain opcodes
- * like destroy qp etc are not safe to be returned success, but this function
- * will be called when FW already reports a timeout. This would be possible
- * only when FW crashes and resets. This will clear all the HW resources.
+ * case #2
+ * If driver detect potential firmware stall, it is not safe state machine
+ * and the driver can not consider all the underlying rdma resources are
+ * freed.
+ * In this state, it is not safe to return success for opcodes related to
+ * destroying rdma resources (like destroy qp, destroy cq etc.).
+ *
+ * Scope of this helper function is only for case #1.
*
* Returns:
* 0 to communicate success to caller.
@@ -417,7 +424,7 @@ static int __send_message_basic_sanity(struct bnxt_qplib_rcfw *rcfw,
/* Prevent posting if f/w is not in a state to process */
if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags))
- return -ENXIO;
+ return bnxt_qplib_map_rc(opcode);
if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags))
return -ETIMEDOUT;
@@ -487,7 +494,7 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
rc = __send_message_basic_sanity(rcfw, msg, opcode);
if (rc)
- return rc == -ENXIO ? bnxt_qplib_map_rc(opcode) : rc;
+ return rc;
rc = __send_message(rcfw, msg, opcode);
if (rc)