From: James Smart jsmart2021@gmail.com
[ Upstream commit 863fbae929c7a5b64e96b8a3ffb34a29eefb9f8f ]
In nvme-fc: it's possible to have connected active controllers and as no references are taken on the LLDD, the LLDD can be unloaded. The controller would enter a reconnect state and as long as the LLDD resumed within the reconnect timeout, the controller would resume. But if a namespace on the controller is the root device, allowing the driver to unload can be problematic. To reload the driver, it may require new io to the boot device, and as it's no longer connected we get into a catch-22 that eventually fails, and the system locks up.
Fix this issue by taking a module reference for every connected controller (which is what the core layer did to the transport module). Reference is cleared when the controller is removed.
Acked-by: Himanshu Madhani hmadhani@marvell.com Reviewed-by: Christoph Hellwig hch@lst.de Signed-off-by: James Smart jsmart2021@gmail.com Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/nvme/host/fc.c | 14 ++++++++++++-- drivers/nvme/target/fcloop.c | 1 + drivers/scsi/lpfc/lpfc_nvme.c | 2 ++ drivers/scsi/qla2xxx/qla_nvme.c | 1 + include/linux/nvme-fc-driver.h | 4 ++++ 5 files changed, 20 insertions(+), 2 deletions(-)
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 058d542647dd..9e4d2ecf736d 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -337,7 +337,8 @@ nvme_fc_register_localport(struct nvme_fc_port_info *pinfo, !template->ls_req || !template->fcp_io || !template->ls_abort || !template->fcp_abort || !template->max_hw_queues || !template->max_sgl_segments || - !template->max_dif_sgl_segments || !template->dma_boundary) { + !template->max_dif_sgl_segments || !template->dma_boundary || + !template->module) { ret = -EINVAL; goto out_reghost_failed; } @@ -1762,6 +1763,7 @@ nvme_fc_ctrl_free(struct kref *ref) { struct nvme_fc_ctrl *ctrl = container_of(ref, struct nvme_fc_ctrl, ref); + struct nvme_fc_lport *lport = ctrl->lport; unsigned long flags;
if (ctrl->ctrl.tagset) { @@ -1787,6 +1789,7 @@ nvme_fc_ctrl_free(struct kref *ref) if (ctrl->ctrl.opts) nvmf_free_options(ctrl->ctrl.opts); kfree(ctrl); + module_put(lport->ops->module); }
static void @@ -2765,10 +2768,15 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, goto out_fail; }
+ if (!try_module_get(lport->ops->module)) { + ret = -EUNATCH; + goto out_free_ctrl; + } + idx = ida_simple_get(&nvme_fc_ctrl_cnt, 0, 0, GFP_KERNEL); if (idx < 0) { ret = -ENOSPC; - goto out_free_ctrl; + goto out_mod_put; }
ctrl->ctrl.opts = opts; @@ -2915,6 +2923,8 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, out_free_ida: put_device(ctrl->dev); ida_simple_remove(&nvme_fc_ctrl_cnt, ctrl->cnum); +out_mod_put: + module_put(lport->ops->module); out_free_ctrl: kfree(ctrl); out_fail: diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 096523d8dd42..b8fe8702065b 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -693,6 +693,7 @@ fcloop_targetport_delete(struct nvmet_fc_target_port *targetport) #define FCLOOP_DMABOUND_4G 0xFFFFFFFF
static struct nvme_fc_port_template fctemplate = { + .module = THIS_MODULE, .localport_delete = fcloop_localport_delete, .remoteport_delete = fcloop_remoteport_delete, .create_queue = fcloop_create_queue, diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c index fcf4b4175d77..af937b91765e 100644 --- a/drivers/scsi/lpfc/lpfc_nvme.c +++ b/drivers/scsi/lpfc/lpfc_nvme.c @@ -1591,6 +1591,8 @@ lpfc_nvme_fcp_abort(struct nvme_fc_local_port *pnvme_lport,
/* Declare and initialization an instance of the FC NVME template. */ static struct nvme_fc_port_template lpfc_nvme_template = { + .module = THIS_MODULE, + /* initiator-based functions */ .localport_delete = lpfc_nvme_localport_delete, .remoteport_delete = lpfc_nvme_remoteport_delete, diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 6b33a1f24f56..7dceed021236 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -578,6 +578,7 @@ static void qla_nvme_remoteport_delete(struct nvme_fc_remote_port *rport) }
static struct nvme_fc_port_template qla_nvme_fc_transport = { + .module = THIS_MODULE, .localport_delete = qla_nvme_localport_delete, .remoteport_delete = qla_nvme_remoteport_delete, .create_queue = qla_nvme_alloc_queue, diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index a726f96010d5..e9c3b98df3e2 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -279,6 +279,8 @@ struct nvme_fc_remote_port { * * Host/Initiator Transport Entrypoints/Parameters: * + * @module: The LLDD module using the interface + * * @localport_delete: The LLDD initiates deletion of a localport via * nvme_fc_deregister_localport(). However, the teardown is * asynchronous. This routine is called upon the completion of the @@ -392,6 +394,8 @@ struct nvme_fc_remote_port { * Value is Mandatory. Allowed to be zero. */ struct nvme_fc_port_template { + struct module *module; + /* initiator-based functions */ void (*localport_delete)(struct nvme_fc_local_port *); void (*remoteport_delete)(struct nvme_fc_remote_port *);