From 4a8842de8db4953fdda7866626b78b12fb8adb97 Mon Sep 17 00:00:00 2001 From: Tomas Henzl Date: Fri, 19 Jan 2018 16:22:05 +0100 Subject: scsi: mpt3sas: fix an out of bound write cpu_msix_table is allocated to store online cpus, but pci_irq_get_affinity may return cpu_possible_mask which is then used to access cpu_msix_table. That causes bad user experience. Fix limits access to only online cpus, I've also added an additional test to protect from an unlikely change in cpu_online_mask. [mkp: checkpatch] Fixes: 1d55abc0e98a ("scsi: mpt3sas: switch to pci_alloc_irq_vectors") Signed-off-by: Tomas Henzl Acked-by: Suganath Prabu Subramani Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'drivers/scsi/mpt3sas') diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 13d6e4ec3022..59a87ca328d3 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -2410,8 +2410,11 @@ _base_assign_reply_queues(struct MPT3SAS_ADAPTER *ioc) continue; } - for_each_cpu(cpu, mask) + for_each_cpu_and(cpu, mask, cpu_online_mask) { + if (cpu >= ioc->cpu_msix_table_sz) + break; ioc->cpu_msix_table[cpu] = reply_q->msix_index; + } } return; } -- cgit v1.2.3 From 9ff549ffb4fb4cc9a4b24d1de9dc3e68287797c4 Mon Sep 17 00:00:00 2001 From: Mauricio Faria de Oliveira Date: Fri, 16 Feb 2018 20:39:57 -0200 Subject: scsi: mpt3sas: fix oops in error handlers after shutdown/unload This patch adds checks for 'ioc->remove_host' in the SCSI error handlers, so not to access pointers/resources potentially freed in the PCI shutdown/module unload path. The error handlers may be invoked after shutdown/unload, depending on other components. This problem was observed with kexec on a system with a mpt3sas based adapter and an infiniband adapter which takes long enough to shutdown: The mpt3sas driver finished shutting down / disabled interrupt handling, thus some commands have not finished and timed out. Since the system was still running (waiting for the infiniband adapter to shutdown), the scsi error handler for task abort of mpt3sas was invoked, and hit an oops -- either in scsih_abort() because 'ioc->scsi_lookup' was NULL without commit dbec4c9040ed ("scsi: mpt3sas: lockless command submission"), or later up in scsih_host_reset() (with or without that commit), because it eventually called mpt3sas_base_get_iocstate(). After the above commit, the oops in scsih_abort() does not occur anymore (_scsih_scsi_lookup_find_by_scmd() is no longer called), but that commit is too big and out of the scope of linux-stable, where this patch might help, so still go for the changes. Also, this might help to prevent similar errors in the future, in case code changes and possibly tries to access freed stuff. Note the fix in scsih_host_reset() is still important anyway. Signed-off-by: Mauricio Faria de Oliveira Acked-by: Sreekanth Reddy Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'drivers/scsi/mpt3sas') diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 74fca184dba9..5ab3caffa08b 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -2835,7 +2835,8 @@ scsih_abort(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { sdev_printk(KERN_INFO, scmd->device, "device been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -2898,7 +2899,8 @@ scsih_dev_reset(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { sdev_printk(KERN_INFO, scmd->device, "device been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -2961,7 +2963,8 @@ scsih_target_reset(struct scsi_cmnd *scmd) _scsih_tm_display_info(ioc, scmd); sas_device_priv_data = scmd->device->hostdata; - if (!sas_device_priv_data || !sas_device_priv_data->sas_target) { + if (!sas_device_priv_data || !sas_device_priv_data->sas_target || + ioc->remove_host) { starget_printk(KERN_INFO, starget, "target been deleted! scmd(%p)\n", scmd); scmd->result = DID_NO_CONNECT << 16; @@ -3019,7 +3022,7 @@ scsih_host_reset(struct scsi_cmnd *scmd) ioc->name, scmd); scsi_print_command(scmd); - if (ioc->is_driver_loading) { + if (ioc->is_driver_loading || ioc->remove_host) { pr_info(MPT3SAS_FMT "Blocking the host reset\n", ioc->name); r = FAILED; -- cgit v1.2.3 From c666d3be99c000bb889a33353e9be0fa5808d3de Mon Sep 17 00:00:00 2001 From: Sreekanth Reddy Date: Fri, 16 Feb 2018 20:39:58 -0200 Subject: scsi: mpt3sas: wait for and flush running commands on shutdown/unload This patch finishes all outstanding SCSI IO commands (but not other commands, e.g., task management) in the shutdown and unload paths. It first waits for the commands to complete (this is done after setting 'ioc->remove_host = 1 ', which prevents new commands to be queued) then it flushes commands that might still be running. This avoids triggering error handling (e.g., abort command) for all commands possibly completed by the adapter after interrupts disabled. [mauricfo: introduced something in commit message.] Signed-off-by: Sreekanth Reddy Tested-by: Mauricio Faria de Oliveira Signed-off-by: Mauricio Faria de Oliveira Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_base.c | 8 ++++---- drivers/scsi/mpt3sas/mpt3sas_base.h | 3 +++ drivers/scsi/mpt3sas/mpt3sas_scsih.c | 10 +++++++++- 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'drivers/scsi/mpt3sas') diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 59a87ca328d3..0aafbfd1b746 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -6297,14 +6297,14 @@ _base_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase) } /** - * _wait_for_commands_to_complete - reset controller + * mpt3sas_wait_for_commands_to_complete - reset controller * @ioc: Pointer to MPT_ADAPTER structure * * This function is waiting 10s for all pending commands to complete * prior to putting controller in reset. */ -static void -_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc) +void +mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc) { u32 ioc_state; @@ -6377,7 +6377,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc, is_fault = 1; } _base_reset_handler(ioc, MPT3_IOC_PRE_RESET); - _wait_for_commands_to_complete(ioc); + mpt3sas_wait_for_commands_to_complete(ioc); _base_mask_interrupts(ioc); r = _base_make_ioc_ready(ioc, type); if (r) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h index 789bc421424b..99ccf83b8c51 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.h +++ b/drivers/scsi/mpt3sas/mpt3sas_base.h @@ -1433,6 +1433,9 @@ void mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc, int mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc); +void +mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc); + /* scsih shared API */ struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index 5ab3caffa08b..c2ea13c7e37e 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -4456,7 +4456,7 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc) st = scsi_cmd_priv(scmd); mpt3sas_base_clear_st(ioc, st); scsi_dma_unmap(scmd); - if (ioc->pci_error_recovery) + if (ioc->pci_error_recovery || ioc->remove_host) scmd->result = DID_NO_CONNECT << 16; else scmd->result = DID_RESET << 16; @@ -9742,6 +9742,10 @@ static void scsih_remove(struct pci_dev *pdev) unsigned long flags; ioc->remove_host = 1; + + mpt3sas_wait_for_commands_to_complete(ioc); + _scsih_flush_running_cmds(ioc); + _scsih_fw_event_cleanup_queue(ioc); spin_lock_irqsave(&ioc->fw_event_lock, flags); @@ -9818,6 +9822,10 @@ scsih_shutdown(struct pci_dev *pdev) unsigned long flags; ioc->remove_host = 1; + + mpt3sas_wait_for_commands_to_complete(ioc); + _scsih_flush_running_cmds(ioc); + _scsih_fw_event_cleanup_queue(ioc); spin_lock_irqsave(&ioc->fw_event_lock, flags); -- cgit v1.2.3 From 864449eea7c600596e305ffdc4a6a846414b222c Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Mon, 26 Feb 2018 15:26:01 +0100 Subject: scsi: mpt3sas: Do not mark fw_event workqueue as WQ_MEM_RECLAIM The firmware event workqueue should not be marked as WQ_MEM_RECLAIM as it's doesn't need to make forward progress under memory pressure. In the current state it will result in a deadlock if the device had been forcefully removed. Cc: Sreekanth Reddy Cc: Suganath Prabu Subramani Acked-by: Sreekanth Reddy Signed-off-by: Hannes Reinecke Signed-off-by: Martin K. Petersen --- drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/scsi/mpt3sas') diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index c2ea13c7e37e..a1cb0236c550 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -10558,7 +10558,7 @@ _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id) snprintf(ioc->firmware_event_name, sizeof(ioc->firmware_event_name), "fw_event_%s%d", ioc->driver_name, ioc->id); ioc->firmware_event_thread = alloc_ordered_workqueue( - ioc->firmware_event_name, WQ_MEM_RECLAIM); + ioc->firmware_event_name, 0); if (!ioc->firmware_event_thread) { pr_err(MPT3SAS_FMT "failure at %s:%d/%s()!\n", ioc->name, __FILE__, __LINE__, __func__); -- cgit v1.2.3