- 03 Aug, 2018 1 commit
-
-
Uma Krishnan authored
[ Upstream commit a3feb6ef ] The following Oops can be encountered if a device removal or system shutdown is initiated while an EEH recovery is in process: [c000000ff2f479c0] c008000015256f18 cxlflash_pci_slot_reset+0xa0/0x100 [cxlflash] [c000000ff2f47a30] c00800000dae22e0 cxl_pci_slot_reset+0x168/0x290 [cxl] [c000000ff2f47ae0] c00000000003ef1c eeh_report_reset+0xec/0x170 [c000000ff2f47b20] c00000000003d0b8 eeh_pe_dev_traverse+0x98/0x170 [c000000ff2f47bb0] c00000000003f80c eeh_handle_normal_event+0x56c/0x580 [c000000ff2f47c60] c00000000003fba4 eeh_handle_event+0x2a4/0x338 [c000000ff2f47d10] c0000000000400b8 eeh_event_handler+0x1f8/0x200 [c000000ff2f47dc0] c00000000013da48 kthread+0x1a8/0x1b0 [c000000ff2f47e30] c00000000000b528 ret_from_kernel_thread+0x5c/0xb4 The remove handler frees AFU memory while the EEH recovery is in progress, leading to a race condition. This can result in a crash if the recovery thread tries to access this memory. To resolve this issue, the cxlflash remove handler will evaluate the device state and yield to any active reset or probing threads. Signed-off-by:
Uma Krishnan <ukrishn@linux.vnet.ibm.com> Acked-by:
Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by:
Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by:
Sasha Levin <alexander.levin@microsoft.com> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
- 16 Feb, 2018 1 commit
-
-
Uma Krishnan authored
commit 96cf727f upstream. In the event of a command failure, cxlflash returns the failure to the upper layers to process. After processing the error, when the command is queued again, the private command structure will not be zeroed and the ioasc could be stale. Per the SISLite specification, the AFU only sets the ioasc in the presence of a failure. Thus, even though the original command succeeds the second time, the command is considered a failure due to stale ioasc. This cycle repeats indefinitely and can cause a hang or IO failure. To fix the issue, clear the ioasc before queuing any command. [mkp: added Cc: stable per request] Fixes: 479ad8e9 ("scsi: cxlflash: Remove zeroing of private command data") Signed-off-by:
-
- 25 Aug, 2017 1 commit
-
-
Matthew R. Ochs authored
The AFU termination sequence has been refactored over time such that the main tear down routine, term_afu(), can no longer can be invoked with a NULL AFU pointer. Remove the unnecessary existence check from term_afu(). Signed-off-by:
-
- 12 Jul, 2017 1 commit
-
-
Dan Carpenter authored
The copy_from/to_user() functions return the number of bytes remaining to be copied but we had intended to return -EFAULT here. Fixes: bc88ac47 ("scsi: cxlflash: Support AFU debug") Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Acked-by:
-
- 01 Jul, 2017 3 commits
-
-
Matthew R. Ochs authored
The device and host reset handler contain debug prints to help identify the entities being reset. Today these reset handlers are based on a SCSI EH design that uses a SCSI command reference as a means of identifying the target entity. As such, the debug trace includes the SCSI command pointer and associated CDB. This is not necessary as the SCSI command is simply the messenger in these scenarios. Refactor the debug prints in the host and reset handlers to only present information that is applicable given the function scope. Signed-off-by:
Hannes Reinecke <hare@suse.com> Signed-off-by:
-
Matthew R. Ochs authored
The current send_tmf() implementation is based on the caller providing a SCSI command reference. In reality all that is needed is a SCSI device reference as the routine uses a private command. Refactor send_tmf() to pass the private adapter configuration reference and a SCSI device reference. As a nice side effect, this will ease the burden of converting caller routines to be based solely off of a SCSI device reference. Signed-off-by:
-
Matthew R. Ochs authored
The device_unregister() service used when cleaning up the character device is already responsible for the internal state associated with the device upon successful creation. As the cxlflash driver does not obtain a second reference to the character device, the explicit call to put_device() is not required and can lead to an inconsistent sysfs among other issues as the reference is no longer valid after the first put_device() is performed. Remove the unnecessary put_device() to remedy this issue. Fixes: a834a36b ("scsi: cxlflash: Create character device to provide host management interface") Signed-off-by:
-
- 26 Jun, 2017 15 commits
-
-
Matthew R. Ochs authored
Currently, the SCSI command presented to the device reset handler is used to send TMFs to the AFU for a device reset. This behavior is incorrect as the command presented is an actual command and not a special notification. As such, it should only be used for reference and not be acted upon. Additionally, the existing TMF transmission routine does not account for actual errors from the hardware, only reflecting failure when a timeout occurs. This can lead to a condition where the device reset handler is presented with a false 'success'. Update send_tmf() to dynamically allocate a private command for sending the TMF command and properly reflect failure when the completed command indicates an error or was aborted. Detect TMF commands during response processing and avoid scsi_done() for these types of commands. Lastly, update comments in the TMF processing paths to describe the new behavior. Signed-off-by:
-
Matthew R. Ochs authored
The SCSI core now zeroes the per-command private data area prior to calling into the LLD. Replace the clearing operation that takes place when the private command data reference is obtained with a routine that performs common initializations. The zeroing that takes place in the device reset path remains intact as the private command data associated with the specified SCSI command is not guaranteed to be cleared. Signed-off-by:
-
Matthew R. Ochs authored
The cxlflash driver supports performing a write-same16 to scrub virtual luns when they are released by a user. To date, AFUs for adapters that are supported by cxlflash do not have the capability to unmap as part of the WS operation. This can lead to fragmented flash devices which results in performance degradation. Future AFUs can optionally support unmap write-same commands and reflects this support via the context control register. This provides userspace applications with direct visibility such that they need not depend on a host API. Detect unmap support during cxlflash initialization by reading the context control register associated with the primary hardware queue. Update the existing write_same16() routine to set the unmap bit in the CDB when unmap is supported by the host. Signed-off-by:
-
Matthew R. Ochs authored
Adopt the SISLite AFU debug capability to allow future CXL Flash adapters the ability to better debug AFU issues. Update the SISLite header with the changes necessary to support AFU debug operations and create a host ioctl interface for user debug software. Also update the cxlflash documentation to describe this new host ioctl. Signed-off-by:
-
Matthew R. Ochs authored
Adopt the SISLite AFU LUN provisioning capability to allow future CXL Flash adapters the ability to better manage storage. Update the SISLite header with the changes necessary to support LUN provision operations and create a host ioctl interface for user LUN management software. Also update the cxlflash documentation to describe this new host ioctl. Signed-off-by:
-
Matthew R. Ochs authored
As staging for supporting various host management functions, add a host ioctl infrastructure to filter ioctl commands and perform operations that are common for all host ioctls. Also update the cxlflash documentation to create a new section for documenting host ioctls. Signed-off-by:
-
Matthew R. Ochs authored
To date the only supported internal AFU command is AFU sync. The logic to send an internal AFU command is embedded in the specific AFU sync handler and would need to be duplicated for new internal AFU commands. In order to support new internal AFU commands, separate code that is common for AFU internal commands into a generic transmission routine and support passing back command status through an IOASA structure. The first user of this new routine is the existing AFU sync command. As a cleanup, use a descriptive name for the AFU sync command instead of a magic number. Signed-off-by:
-
Uma Krishnan authored
The cxlflash driver currently lacks host management interface. Future devices supported by cxlflash will provide a variety of host-wide management functions. Examples include LUN provisioning, hardware debug support, and firmware download. In order to provide a way to manage the device, a character device will be created during probe of each adapter. This device will support a set of ioctls defined in the SISLite specification from which administrators can manage the adapter. Signed-off-by:
-
Uma Krishnan authored
To date, CXL flash devices do not support a single command abort operation. Instead, the SISLite specification provides a context reset operation to cleanup all pending commands for a given context. When a context reset is successful, it is guaranteed that the AFU has aborted all currently pending I/O. This sequence is less invasive than a device or host reset and can be executed to support scsi command abort requests. Add eh_abort_handler callback support to process command timeouts and abort requests. Signed-off-by:
-
Uma Krishnan authored
When the AFU is reset in an error path, pending scsi commands can be silently dropped without completion or a formal abort. This puts the onus on the cxlflash driver to notify mid-layer and indicating that the command can be retried. Once the card has been quiesced, the hardware send queue lock is acquired to prevent any data movement while the pending commands are processed. Signed-off-by:
-
Uma Krishnan authored
Currently, there is no book keeping of the pending scsi commands in the cxlflash driver. This lack of tracking in-flight requests is too restrictive and requires a heavy-hammer reset each time an adapter error is encountered. Additionally, it does not allow for commands to be properly retried. In order to avoid this problem and to better handle error path command cleanup, introduce a linked list for each hardware queue that tracks pending commands. Signed-off-by:
-
Uma Krishnan authored
A context reset failure indicates the AFU is in a bad state. At present, when such a situation occurs, no further action is taken. This leaves the adapter in an unusable state with no recoverable actions. To avoid this situation, context reset failures will be escalated to a host reset operation. This will be done asynchronously to allow the acting thread to return to the user with a failure. Signed-off-by:
-
Uma Krishnan authored
Per the SISLite specification, context_reset() writes 0x1 to the LSB of the reset register. When the AFU processes this reset request, it is expected to clear the bit after reset is complete. The current implementation simply checks that the entire value read back is not 1, instead of masking off the LSB and evaluating it for a change to 0. Should the AFU manipulate other bits during the reset (reading back a value of 0xF for example), successful completion will be prematurely indicated given the existing logic. Additionally, in the event that the context reset operation fails, there does not currently exist a way to provide feedback to the initiator of the reset. This poses a problem for the rare case that a context reset fails as the caller will proceed on the assumption that all is well. To remedy these issues, refactor the context reset routine to only mask off the LSB when evaluating for success and return status to the caller. Also update the context reset handler parameters to pass a hardware queue reference instead of a single command to better reflect that the entire queue associated with the context is impacted by the reset. Signed-off-by:
-
Uma Krishnan authored
The cxlflash_afu_sync() routine returns a negative one to indicate any kind of failure. This makes it impossible to establish why the error occurred. Update the return codes to clearly indicate the failure cause to the caller. Signed-off-by:
-
Uma Krishnan authored
Currently there are separate spin locks for the two supported I/O queueing models. This makes it difficult to serialize with paths outside the enqueue path. As a design simplification and to support serialization with enqueue operations, move to only a single lock that is used for enqueueing regardless of the queueing model. Signed-off-by:
-
- 14 Apr, 2017 16 commits
-
-
Matthew R. Ochs authored
As an enhancement to distribute requests to multiple hardware queues, add the infrastructure to hash a SCSI command into a particular hardware queue. Support the following scenarios when deriving which queue to use: single queue, tagging when SCSI-MQ enabled, and simple hash via CPU ID when SCSI-MQ is disabled. Rather than altering the existing send API, the derived hardware queue is stored in the AFU command where it can be used for sending a command to the chosen hardware queue. Signed-off-by:
-
Matthew R. Ochs authored
As staging for supporting multiple hardware queues, add an attribute to show and set the current number of hardware queues for the host. Support specifying a hard limit or a CPU affinitized value. This will allow the number of hardware queues to be tuned by a system administrator. Signed-off-by:
-
Uma Krishnan authored
Introduce multiple hardware queues to improve legacy I/O path performance. Each hardware queue is comprised of a master context and associated I/O resources. The hardware queues are initially implemented as a static array embedded in the AFU. This will be transitioned to a dynamic allocation in a later series to improve the memory footprint of the driver. Signed-off-by:
-
Matthew R. Ochs authored
The method used to decode asynchronous interrupts involves unnecessary loops to match up bits that are set with corresponding entries in the asynchronous interrupt information table. This algorithm is wasteful and does not scale well as new status bits are supported. As an improvement, use the for_each_set_bit() service to iterate over the asynchronous status bits and refactor the information table such that it can be indexed by bit position. Signed-off-by:
-
Matthew R. Ochs authored
Validation statements to enforce assumptions about specific defines are not being evaluated by the compiler due to the fact that they reside in a routine that is not used. To activate them, call the routine as part of module initialization. As an additional, related cleanup, remove the now-defunct CXLFLASH_NUM_CMDS. Signed-off-by:
-
Matthew R. Ochs authored
Devices supported by the cxlflash driver are fully coherent and do not require a bus address mapping. Avoid unnecessary path length by using the virtual address and length already present in the scatter-gather entry. Signed-off-by:
-
Matthew R. Ochs authored
An EEH during probe can lead to a crash as the recovery thread races with the probe thread. To avoid this issue, introduce new states to fence out EEH recovery until probe has completed. Also ensure the reset wait queue is flushed during device removal to avoid orphaned threads. Signed-off-by:
-
Matthew R. Ochs authored
Update the driver to allow for future cards with 4 ports. Signed-off-by:
-
Matthew R. Ochs authored
Update the SISlite header to support 4 ports as outlined in the SISlite specification. Address fallout from structure renames and refreshed organization throughout the driver. Determine the number of ports supported by a card from the global port selection mask register reset value. Signed-off-by:
-
Matthew R. Ochs authored
As staging to support FC-related updates to the SISlite specification, introduce helper routines to obtain references to FC resources that exist within the global map. This will allow changes to the underlying global map structure without impacting existing code paths. Signed-off-by:
-
Matthew R. Ochs authored
At present, the cxlflash driver only supports hardware with two FC ports. The code was initially designed with this assumption and is dependent on having two FC ports - adding more ports will break logic within the driver. To mitigate this issue, remove the existing port assumptions and transition the code to support more than two ports. As a side effect, clarify the interpretation of the DK_CXLFLASH_ALL_PORTS_ACTIVE flag. Signed-off-by:
-
Matthew R. Ochs authored
Transition from a static number of FC ports to a value that is derived during probe. For now, a static value is used but this will later be based on the type of card being configured. Signed-off-by:
-
Matthew R. Ochs authored
As staging for future function, pass the config pointer instead of the AFU pointer for port-related sysfs helper routines. Signed-off-by:
-
Matthew R. Ochs authored
Currently, RRQ processing takes place on hardware interrupt context. This can be a heavy burden in some environments due to the overhead encountered while completing RRQ entries. In an effort to improve system performance, use the IRQ polling API to schedule this processing on softirq context. This function will be disabled by default until starting values can be established for the hardware supported by this driver. Signed-off-by:
-
Matthew R. Ochs authored
As further staging to support processing the HRRQ by other means, access to the HRRQ needs to be serialized by a disabled lock. This will allow safe access in other non-hardware interrupt contexts. In an effort to minimize the period where interrupts are disabled, support is added to queue up commands harvested from the RRQ such that they can be processed with hardware interrupts enabled. While this doesn't offer any improvement with processing on a hardware interrupt it will help when IRQ polling is supported and the command completions can execute on softirq context. Signed-off-by:
-
Matthew R. Ochs authored
In order to support processing the HRRQ by other means (e.g. polling), the processing portion of the current RRQ interrupt handler needs to be broken out into a separate routine. This will allow RRQ processing from places other than the RRQ hardware interrupt handler. Signed-off-by:
-
- 22 Feb, 2017 1 commit
-
-
Matthew R. Ochs authored
Add support for a future IBM Coherent Accelerator (CXL) flash AFU with an ID of 0x0624. Signed-off-by:
-
- 12 Jan, 2017 1 commit
-
-
Uma Krishnan authored
When processing an AFU asynchronous interrupt, if the action results in an operation that requires off level processing (a link reset for example), the worker thread is scheduled. In the meantime a reset event (i.e.: EEH) could unmap the AFU to recover. This results in an Oops when the worker thread tries to access the AFU mapping. [c000000f17e03b90] d000000007cd5978 cxlflash_worker_thread+0x268/0x550 [c000000f17e03c40] c00000000011883c process_one_work+0x1dc/0x680 [c000000f17e03ce0] c000000000118e80 worker_thread+0x1a0/0x520 [c000000f17e03d80] c000000000126174 kthread+0xf4/0x100 [c000000f17e03e30] c00000000000a47c ret_from_kernel_thread+0x5c/0xe0 In an effort to avoid this, a mapcount was introduced in commit b45cdbaf ("cxlflash: Resolve oops in wait_port_offline") but due to the race condition described above, this solution is incomplete. In order to fully resolve this problem and to simplify things, this commit removes the mapcount solution. Instead, the scheduled worker thread is cancelled after interrupts have been disabled and prior to the mapping being freed. Fixes: b45cdbaf ("cxlflash: Resolve oops in wait_port_offline") Signed-off-by:
-
