From 1d3324c382b1a617eb567e3650dcb51f22dfec9a Mon Sep 17 00:00:00 2001 From: "Matthew R. Ochs" Date: Fri, 2 Sep 2016 15:39:30 -0500 Subject: [PATCH] scsi: cxlflash: Fix to avoid EEH and host reset collisions The EEH reset handler is ignorant to the current state of the driver when processing a frozen event and initiating a device reset. This can be an issue if an EEH event occurs while a user or stack initiated reset is executing. More specifically, if an EEH occurs while the SCSI host reset handler is active, the reset initiated by the EEH thread will likely collide with the host reset thread. This can leave the device in an inconsistent state, or worse, cause a system crash. As a remedy, the EEH handler is updated to evaluate the device state and take appropriate action (proceed, wait, or disconnect host). The host reset handler is also updated to handle situations where an EEH occurred during a host reset. In such situations, the host reset handler will delay reporting back a success to give the EEH reset an opportunity to complete. Signed-off-by: Matthew R. Ochs Acked-by: Uma Krishnan Signed-off-by: Martin K. Petersen --- drivers/scsi/cxlflash/main.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 4c2559adf723..4ef523505364 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -2042,6 +2042,11 @@ retry: * cxlflash_eh_host_reset_handler() - reset the host adapter * @scp: SCSI command from stack identifying host. * + * Following a reset, the state is evaluated again in case an EEH occurred + * during the reset. In such a scenario, the host reset will either yield + * until the EEH recovery is complete or return success or failure based + * upon the current device state. + * * Return: * SUCCESS as defined in scsi/scsi.h * FAILED as defined in scsi/scsi.h @@ -2074,7 +2079,8 @@ static int cxlflash_eh_host_reset_handler(struct scsi_cmnd *scp) } else cfg->state = STATE_NORMAL; wake_up_all(&cfg->reset_waitq); - break; + ssleep(1); + /* fall through */ case STATE_RESET: wait_event(cfg->reset_waitq, cfg->state != STATE_RESET); if (cfg->state == STATE_NORMAL) @@ -2590,6 +2596,9 @@ out_remove: * @pdev: PCI device struct. * @state: PCI channel state. * + * When an EEH occurs during an active reset, wait until the reset is + * complete and then take action based upon the device state. + * * Return: PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT */ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev, @@ -2603,6 +2612,10 @@ static pci_ers_result_t cxlflash_pci_error_detected(struct pci_dev *pdev, switch (state) { case pci_channel_io_frozen: + wait_event(cfg->reset_waitq, cfg->state != STATE_RESET); + if (cfg->state == STATE_FAILTERM) + return PCI_ERS_RESULT_DISCONNECT; + cfg->state = STATE_RESET; scsi_block_requests(cfg->host); drain_ioctls(cfg); -- 2.39.5