@@ -138,6 +138,7 @@ struct bnxt_re_dev {
#define BNXT_RE_FLAG_QOS_WORK_REG 5
#define BNXT_RE_FLAG_RESOURCES_ALLOCATED 7
#define BNXT_RE_FLAG_RESOURCES_INITIALIZED 8
+#define BNXT_RE_FLAG_ERR_DEVICE_DETACHED 17
#define BNXT_RE_FLAG_ISSUE_ROCE_STATS 29
struct net_device *netdev;
unsigned int version, major, minor;
@@ -81,6 +81,7 @@ static struct workqueue_struct *bnxt_re_wq;
static void bnxt_re_remove_device(struct bnxt_re_dev *rdev);
static void bnxt_re_dealloc_driver(struct ib_device *ib_dev);
static void bnxt_re_stop_irq(void *handle);
+static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev);
static void bnxt_re_set_drv_mode(struct bnxt_re_dev *rdev, u8 mode)
{
@@ -221,6 +222,37 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev)
/* for handling bnxt_en callbacks later */
static void bnxt_re_stop(void *p)
{
+ struct bnxt_re_dev *rdev = p;
+ struct bnxt *bp;
+
+ if (!rdev)
+ return;
+ ASSERT_RTNL();
+
+ /* L2 driver invokes this callback during device error/crash or device
+ * reset. Current RoCE driver doesn't recover the device in case of
+ * error. Handle the error by dispatching fatal events to all qps
+ * ie. by calling bnxt_re_dev_stop and release the MSIx vectors as
+ * L2 driver want to modify the MSIx table.
+ */
+ bp = netdev_priv(rdev->netdev);
+
+ ibdev_info(&rdev->ibdev, "Handle device stop call from L2 driver");
+ /* Check the current device state from L2 structure and move the
+ * device to detached state if FW_FATAL_COND is set.
+ * This prevents more commands to HW during clean-up,
+ * in case the device is already in error.
+ */
+ if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state))
+ set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags);
+
+ bnxt_re_dev_stop(rdev);
+ bnxt_re_stop_irq(rdev);
+ /* Move the device states to detached and avoid sending any more
+ * commands to HW
+ */
+ set_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags);
+ set_bit(ERR_DEVICE_DETACHED, &rdev->rcfw.cmdq.flags);
}
static void bnxt_re_start(void *p)
@@ -234,6 +266,8 @@ static void bnxt_re_sriov_config(void *p, int num_vfs)
if (!rdev)
return;
+ if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
+ return;
rdev->num_vfs = num_vfs;
if (!bnxt_qplib_is_chip_gen_p5(rdev->chip_ctx)) {
bnxt_re_set_resource_limits(rdev);
@@ -427,6 +461,9 @@ static int bnxt_re_net_ring_free(struct bnxt_re_dev *rdev,
if (!en_dev)
return rc;
+ if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
+ return 0;
+
memset(&fw_msg, 0, sizeof(fw_msg));
bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_RING_FREE, -1, -1);
@@ -489,6 +526,9 @@ static int bnxt_re_net_stats_ctx_free(struct bnxt_re_dev *rdev,
if (!en_dev)
return rc;
+ if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags))
+ return 0;
+
memset(&fw_msg, 0, sizeof(fw_msg));
bnxt_re_init_hwrm_hdr(rdev, (void *)&req, HWRM_STAT_CTX_FREE, -1, -1);
@@ -212,6 +212,10 @@ int bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
u8 opcode, retry_cnt = 0xFF;
int rc = 0;
+ /* Prevent posting if f/w is not in a state to process */
+ if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags))
+ return 0;
+
do {
opcode = req->opcode;
rc = __send_message(rcfw, req, resp, sb, is_block);
@@ -138,6 +138,8 @@ struct bnxt_qplib_qp_node {
#define FIRMWARE_INITIALIZED_FLAG (0)
#define FIRMWARE_FIRST_FLAG (31)
#define FIRMWARE_TIMED_OUT (3)
+#define ERR_DEVICE_DETACHED (4)
+
struct bnxt_qplib_cmdq_mbox {
struct bnxt_qplib_reg_desc reg;
void __iomem *prod;