"Interrupt handle revoked" is an event that happens when the driver is
running on a guest kernel and the VM is migrated to a new machine.
The device will trigger an interrupt that signals to the guest driver
that the interrupt handles need to be replaced.
The misc irq thread function calls a helper function to handle the
event. The function uses the WQ percpu_ref to quiesce the kernel
submissions. It then replaces the interrupt handles by requesting
interrupt handle command for each I/O MSIX vector. Once the handle is
updated, the driver will unblock the submission path to allow new
submissions.
The submitter will attempt to acquire a percpu_ref before submission. When
the request fails, it will wait on the wq_resurrect 'completion'.
The driver does anticipate the possibility of descriptors being submitted
before the WQ percpu_ref is killed. If a descriptor has already been
submitted, it will return with incorrect interrupt handle status. The
descriptor will be re-submitted with the new interrupt handle on the
completion path. For descriptors with incorrect interrupt handles,
completion interrupt won't be triggered.
At the completion of the interrupt handle refresh, the handling function
will call idxd_int_handle_refresh_drain() to issue drain descriptors to
each of the wq with associated interrupt handle. The drain descriptor will have
interrupt request set but without completion record. This will ensure all
descriptors with incorrect interrupt completion handle get drained and
a completion interrupt is triggered for the guest driver to process them.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Co-Developed-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163528420189.3925689.18212568593220415551.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Handle a descriptor that has been marked with invalid interrupt handle
error in status. Create a work item that will resubmit the descriptor. This
typically happens when the driver has handled the revoke interrupt handle
event and has a new interrupt handle.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163528419601.3925689.4166517602890523193.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add a locked version of idxd_quiesce() call so that the quiesce can be
called with a lock in situations where the lock is not held by the caller.
In the driver probe/remove path, the lock is already held, so the raw
version can be called w/o locking.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163528418980.3925689.5841907054957931211.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Attach int_handle to irq_entry. This removes the separate management of int
handles and reduces the confusion of interating through int handles that is
off by 1 count.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163528417065.3925689.11505755433684476288.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Refactor the completion function to allow skipping of descriptor freeing on
the submission failure path. This completely removes descriptor freeing
from the submit failure path and leave the responsibility to the caller.
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163528416222.3925689.12859769271667814762.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
According to core-api/dma-api-howto.rst, the address from
dma_alloc_coherent is gauranteed to align to the smallest PAGE_SIZE order.
That supercedes the 64B/32B alignment requirement of the completion record.
Remove alignment adjustment code.
Tested-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/163517396063.3484297.7494385225280705372.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Enabling device and wq returns standard errno and that does not provide
enough details to indicate what exactly failed. The hardware command status
is only 8bits. Expand the command status to 32bits and use the upper 16
bits to define software errors to provide more details on the exact
failure. Bit 31 will be used to indicate the error is software set as the
driver is using some of the spec defined hardware error as well.
Cc: Ramesh Thomas <ramesh.thomas@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162681373579.1968485.5891788397526827892.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The device submission portal is on a 4k page and any of those 64bit aligned
address on the page can be used for descriptor submission. By rotating the
offset through the 4k range and prevent successive writes to the same MMIO
address, performance improvement is observed through testing.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162681372446.1968485.10634280461681015569.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Set GRPCFG traffic class to value of 1 for best performance on current
generation of accelerators. Also add override option to allow experimentation.
Sysfs knobs are disabled for DSA/IAX gen1 devices.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162681373005.1968485.3761065664382799202.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The original architecture of /sys/bus/dsa invented a scheme whereby
a single entry in the list of bus drivers, /sys/bus/drivers/dsa,
handled all device types and internally routed them to different
different drivers. Those internal drivers were invisible to
userspace.
With the idxd driver transitioned to a proper bus device-driver model,
the legacy behavior needs to be preserved due to it being exposed to
user space via sysfs. Create a compat driver to provide the legacy
behavior for /sys/bus/dsa/drivers/dsa. This should satisfy user
tool accel-config v3.2 or ealier where this behavior is expected.
If the distro has a newer accel-config then the legacy mode does
not need to be enabled.
When the compat driver binds the device (i.e. dsa0) to the dsa driver,
it will be bound to the new idxd_drv. The wq device (i.e. wq0.0) will
be bound to either the dmaengine_drv or the user_drv. The dsa_drv
becomes a routing mechansim for the new drivers. It will not support
additional external drivers that are implemented later.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637468705.744545.4399080971745974435.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The original architecture of /sys/bus/dsa invented a scheme whereby a
single entry in the list of bus drivers, /sys/bus/drivers/dsa, handled
all device types and internally routed them to different drivers.
Those internal drivers were invisible to userspace. Now, as
/sys/bus/dsa wants to grow support for alternate drivers for a given
device, for example vfio-mdev instead of kernel-internal-dmaengine, a
proper bus device-driver model is needed. The first step in that process
is separating the existing omnibus/implicit "dsa" driver into proper
individual drivers registered on /sys/bus/dsa. Establish the
idxd_user_drv driver that controls the enabling and disabling of the
wq and also register and unregister a char device to allow user space
to mmap the descriptor submission portal.
The cdev related bits are moved to the cdev driver probe/remove and out of
the drv_enabe/disable_wq() calls. These bits are exclusive to the cdev
operation and not part of the generic enable/disable of the wq device.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637467578.744545.10203997610072341376.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The original architecture of /sys/bus/dsa invented a scheme whereby a
single entry in the list of bus drivers, /sys/bus/drivers/dsa, handled
all device types and internally routed them to different drivers.
Those internal drivers were invisible to userspace. Now, as
/sys/bus/dsa wants to grow support for alternate drivers for a given
device, for example vfio-mdev instead of kernel-internal-dmaengine, a
proper bus device-driver model is needed. The first step in that process
is separating the existing omnibus/implicit "dsa" driver into proper
individual drivers registered on /sys/bus/dsa. Establish the
idxd_dmaengine_drv driver that controls the enabling and disabling of the
wq and also register and unregister the dma channel.
idxd_wq_alloc_resources() and idxd_wq_free_resources() also get moved to
the dmaengine driver. The resources (dma descriptors allocation and setup)
are only used by the dmaengine driver and should only happen when it loads.
The char dev driver (cdev) related bits are left in the __drv_enable_wq()
and __drv_disable_wq() calls to be moved when we split out the char dev
driver just like how the dmaengine driver is split out.
WQ autoload support is not expected currently. With the amount of
configuration needed for the device, the wq is always expected to
be enabled by a tool (or via sysfs) rather than auto enabled at driver
load.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637467033.744545.12330636655625405394.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The original architecture of /sys/bus/dsa invented a scheme whereby a
single entry in the list of bus drivers, /sys/bus/drivers/dsa, handled
all device types and internally routed them to different drivers.
Those internal drivers were invisible to userspace. Now, as
/sys/bus/dsa wants to grow support for alternate drivers for a given
device, for example vfio-mdev instead of kernel-internal-dmaengine, a
proper bus device-driver model is needed. The first step in that process
is separating the existing omnibus/implicit "dsa" driver into proper
individual drivers registered on /sys/bus/dsa. Establish the idxd_drv
driver that control the enabling and disabling of the accelerator device.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637466439.744545.15210886092627144577.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add an array of support device types to the idxd_device_driver
definition in order to enable simple matching of device type to a
given driver. The deprecated / omnibus dsa_drv driver specifies
IDXD_DEV_NONE as its only role is to service legacy userspace (old
accel-config) directed bind requests and route them to them the proper
driver. It need not attach to a device when the bus is autoprobed. The
accel-config tooling is being updated to drop its dependency on this
deprecated bind scheme.
Reviewed-by: Dan Willliams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637465882.744545.17456174666211577867.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Current implementation have put all the code that should be in a driver
probe/remove in the bus probe/remove function. Add ->probe() and ->remove()
support for the dsa_drv and move all those code out of bus probe/remove.
The change does not split out the distinction between device sub-driver and
wq sub-driver. It only cleans up the bus calls. The split out will be
addressed in follow on patches.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637463586.744545.5806250155539938643.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The IDXD_DEV_CONF_READY state flag is no longer needed. The current
implementation uses this flag to stop the device from doing
configuration until the pci driver probe has completed. With the
driver architecture going towards multiple sub-driver attached to
the dsa_bus, this is no longer feasible. The sub-drivers will be
allowed to probe and return with failure when they are not ready
to complete the probe rather than using a state flag to gate the
probing.
There is no expectation that the devices auto-attach to a driver.
Userspace configuration is expected to setup the device before
enabling.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637460633.744545.8902095097471365420.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add a 'struct idxd_dev' that wraps the 'struct device' for idxd conf_dev
that registers with the dsa bus. This is introduced in order to deal with
multiple different types of 'devices' that are registered on the dsa_bus
when the compat driver needs to route them to the correct driver to attach.
The bind() call now can determine the type of device and then do the
appropriate driver matching.
Reviewed-by Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637460065.744545.584492831446090984.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add helper functions for dsa-driver registration similar to other
bus-types. In particular, do not require dsa-drivers to open-code the
bus, owner, and mod_name fields. Let registration and unregistration
operate on the 'struct idxd_device_driver' instead of the raw /
embedded 'struct device_driver'.
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162637458949.744545.14996726325385482050.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Konstantin observed that when descriptors are submitted, the descriptor is
added to the pending list after the submission. This creates a race window
with the slight possibility that the descriptor can complete before it
gets added to the pending list and this window would cause the completion
handler to miss processing the descriptor.
To address the issue, the addition of the descriptor to the pending list
must be done before it gets submitted to the hardware. However, submitting
to swq with ENQCMDS instruction can cause a failure with the condition of
either wq is full or wq is not "active".
With the descriptor allocation being the gate to the wq capacity, it is not
possible to hit a retry with ENQCMDS submission to the swq. The only
possible failure can happen is when wq is no longer "active" due to hw
error and therefore we are moving towards taking down the portal. Given
this is a rare condition and there's no longer concern over I/O
performance, the driver can walk the completion lists in order to retrieve
and abort the descriptor.
The error path will set the descriptor to aborted status. It will take the
work list lock to prevent further processing of worklist. It will do a
delete_all on the pending llist to retrieve all descriptors on the pending
llist. The delete_all action does not require a lock. It will walk through
the acquired llist to find the aborted descriptor while add all remaining
descriptors to the work list since it holds the lock. If it does not find
the aborted descriptor on the llist, it will walk through the work
list. And if it still does not find the descriptor, then it means the
interrupt handler has removed the desc from the llist but is pending on
the work list lock and will process it once the error path releases the
lock.
Fixes: eb15e7154f ("dmaengine: idxd: add interrupt handle request and release support")
Reported-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162628855747.360485.10101925573082466530.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
IOPS increased when changing MSIX vector to per WQ from roundrobin.
Allows descriptor to be completed by the submitter improves caching
locality.
Suggested-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
Link: https://lore.kernel.org/r/162456717326.1130457.15258077196523268356.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The previous state cleanup patch only performed wq state cleanups. This
does not go far enough as when device is disabled or reset, the state
for groups and engines must also be cleaned up. Add additional state
cleanup beyond wq cleanup. Tie those cleanups directly to device
disable and reset, and wq disable and reset.
Fixes: da32b28c95 ("dmaengine: idxd: cleanup workqueue config after disabling")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/162285154108.2096632.5572805472362321307.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Implement the IDXD performance monitor capability (named 'perfmon' in
the DSA (Data Streaming Accelerator) spec [1]), which supports the
collection of information about key events occurring during DSA and
IAX (Intel Analytics Accelerator) device execution, to assist in
performance tuning and debugging.
The idxd perfmon support is implemented as part of the IDXD driver and
interfaces with the Linux perf framework. It has several features in
common with the existing uncore pmu support:
- it does not support sampling
- does not support per-thread counting
However it also has some unique features not present in the core and
uncore support:
- all general-purpose counters are identical, thus no event constraints
- operation is always system-wide
While the core perf subsystem assumes that all counters are by default
per-cpu, the uncore pmus are socket-scoped and use a cpu mask to
restrict counting to one cpu from each socket. IDXD counters use a
similar strategy but expand the scope even further; since IDXD
counters are system-wide and can be read from any cpu, the IDXD perf
driver picks a single cpu to do the work (with cpu hotplug notifiers
to choose a different cpu if the chosen one is taken off-line).
More specifically, the perf userspace tool by default opens a counter
for each cpu for an event. However, if it finds a cpumask file
associated with the pmu under sysfs, as is the case with the uncore
pmus, it will open counters only on the cpus specified by the cpumask.
Since perfmon only needs to open a single counter per event for a
given IDXD device, the perfmon driver will create a sysfs cpumask file
for the device and insert the first cpu of the system into it. When a
user uses perf to open an event, perf will open a single counter on
the cpu specified by the cpu mask. This amounts to the default
system-wide rather than per-cpu counting mentioned previously for
perfmon pmu events. In order to keep the cpu mask up-to-date, the
driver implements cpu hotplug support for multiple devices, as IDXD
usually enumerates and registers more than one idxd device.
The perfmon driver implements basic perfmon hardware capability
discovery and configuration, and is initialized by the IDXD driver's
probe function. During initialization, the driver retrieves the total
number of supported performance counters, the pmu ID, and the device
type from idxd device, and registers itself under the Linux perf
framework.
The perf userspace tool can be used to monitor single or multiple
events depending on the given configuration, as well as event groups,
which are also supported by the perfmon driver. The user configures
events using the perf tool command-line interface by specifying the
event and corresponding event category, along with an optional set of
filters that can be used to restrict counting to specific work queues,
traffic classes, page and transfer sizes, and engines (See [1] for
specifics).
With the configuration specified by the user, the perf tool issues a
system call passing that information to the kernel, which uses it to
initialize the specified event(s). The event(s) are opened and
started, and following termination of the perf command, they're
stopped. At that point, the perfmon driver will read the latest count
for the event(s), calculate the difference between the latest counter
values and previously tracked counter values, and display the final
incremental count as the event count for the cycle. An overflow
handler registered on the IDXD irq path is used to account for counter
overflows, which are signaled by an overflow interrupt.
Below are a couple of examples of perf usage for monitoring DSA events.
The following monitors all events in the 'engine' category. Becuuse
no filters are specified, this captures all engine events for the
workload, which in this case is 19 iterations of the work generated by
the kernel dmatest module.
Details describing the events can be found in Appendix D of [1],
Performance Monitoring Events, but briefly they are:
event 0x1: total input data processed, in 32-byte units
event 0x2: total data written, in 32-byte units
event 0x4: number of work descriptors that read the source
event 0x8: number of work descriptors that write the destination
event 0x10: number of work descriptors dispatched from batch descriptors
event 0x20: number of work descriptors dispatched from work queues
# perf stat -e dsa0/event=0x1,event_category=0x1/,
dsa0/event=0x2,event_category=0x1/,
dsa0/event=0x4,event_category=0x1/,
dsa0/event=0x8,event_category=0x1/,
dsa0/event=0x10,event_category=0x1/,
dsa0/event=0x20,event_category=0x1/
modprobe dmatest channel=dma0chan0 timeout=2000
iterations=19 run=1 wait=1
Performance counter stats for 'system wide':
5,332 dsa0/event=0x1,event_category=0x1/
5,327 dsa0/event=0x2,event_category=0x1/
19 dsa0/event=0x4,event_category=0x1/
19 dsa0/event=0x8,event_category=0x1/
0 dsa0/event=0x10,event_category=0x1/
19 dsa0/event=0x20,event_category=0x1/
21.977436186 seconds time elapsed
The command below illustrates filter usage with a simple example. It
specifies that MEM_MOVE operations should be counted for the DSA
device dsa0 (event 0x8 corresponds to the EV_MEM_MOVE event - Number
of Memory Move Descriptors, which is part of event category 0x3 -
Operations. The detailed category and event IDs are available in
Appendix D, Performance Monitoring Events, of [1]). In addition to
the event and event category, a number of filters are also specified
(the detailed filter values are available in Chapter 6.4 (Filter
Support) of [1]), which will restrict counting to only those events
that meet all of the filter criteria. In this case, the filters
specify that only MEM_MOVE operations that are serviced by work queue
wq0 and specifically engine number engine0 and traffic class tc0
having sizes between 0 and 4k and page size of between 0 and 1G result
in a counter hit; anything else will be filtered out and not appear in
the final count. Note that filters are optional - any filter not
specified is assumed to be all ones and will pass anything.
# perf stat -e dsa0/filter_wq=0x1,filter_tc=0x1,filter_sz=0x7,
filter_eng=0x1,event=0x8,event_category=0x3/
modprobe dmatest channel=dma0chan0 timeout=2000
iterations=19 run=1 wait=1
Performance counter stats for 'system wide':
19 dsa0/filter_wq=0x1,filter_tc=0x1,filter_sz=0x7,
filter_eng=0x1,event=0x8,event_category=0x3/
21.865914091 seconds time elapsed
The output above reflects that the unspecified workload resulted in
the counting of 19 MEM_MOVE operation events that met the filter
criteria.
[1]: https://software.intel.com/content/www/us/en/develop/download/intel-data-streaming-accelerator-preliminary-architecture-specification.html
[ Based on work originally by Jing Lin. ]
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Link: https://lore.kernel.org/r/0c5080a7d541904c4ad42b848c76a1ce056ddac7.1619276133.git.zanussi@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Remove interrupt masking and just let the hard irq handler keep
firing for new events. This is less of a performance impact vs
the MMIO readback inside the pci_msi_{mask,unmas}_irq(). Especially
with a loaded system those flushes can be stuck behind large amounts
of MMIO writes to flush. When guest kernel is running on top of VFIO
mdev, mask/unmask causes a vmexit each time and is not desirable.
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/161894523436.3210025.1834640110556139277.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Create a dedicated lock for device command operations. Put the device
command operation under finer grained locking instead of using the
idxd->dev_lock.
Suggested-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161894525685.3210132.16160045731436382560.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
DSA spec states that when Request Interrupt Handle and Release Interrupt
Handle command bits are set in the CMDCAP register, these device commands
must be supported by the driver.
The interrupt handle is programmed in a descriptor. When Request Interrupt
Handle is not supported, the interrupt handle is the index of the desired
entry in the MSI-X table. When the command is supported, driver must use
the command to obtain a handle to be programmed in the submitted
descriptor.
A requested handle may be revoked. After the handle is revoked, any use of
the handle will result in Invalid Interrupt Handle error.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161894439422.3202472.17579543737810265471.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The read-only configuration mode is defined by the DSA spec as a mode of
the device WQ configuration. When GENCAP register bit 31 is set to 0,
the device is in RO mode and group configuration and some fields of the
workqueue configuration registers are read-only and reflect the fixed
configuration of the device. Add support for RO mode. The driver will
load the values from the registers directly setup all the internally
cached data structures based on the device configuration.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161894438847.3202472.6317563824045432727.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Current submission path has no way to restrict the submitter from
stop submiting on shutdown path or wq disable path. This provides a way to
quiesce the submission path.
Modeling after 'struct reqeust_queue' usage of percpu_ref. One of the
abilities of per_cpu reference counting is the ability to stop new
references from being taken while awaiting outstanding references to be
dropped. On wq shutdown, we want to block any new submissions to the kernel
workqueue and quiesce before disabling. The percpu_ref allows us to block
any new submissions and wait for any current submission calls to finish
submitting to the workqueue.
A percpu_ref is embedded in each idxd_wq context to allow control for
individual wq. The wq->wq_active counter is elevated before calling
movdir64b() or enqcmds() to submit a descriptor to the wq and dropped once
the submission call completes. The function is gated by
percpu_ref_tryget_live(). On shutdown with percpu_ref_kill() called, any
new submission would be blocked from acquiring a ref and failed. Once all
references are dropped for the wq, shutdown can continue.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161894438293.3202472.14894701611500822232.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Move all static data type for per device type to an idxd_driver_data data
structure. The data can be attached to the pci_device_id and provided by
the pci probe function. This removes a lot of unnecessary type detection
and setup code.
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161852988924.2203940.2787590808682466398.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
There is no need to have an additional bus for the IAX device. The removal
of IAX will change user ABI as /sys/bus/iax will no longer exist.
The iax device will be moved to the dsa bus. The device id for dsa and
iax will now be combined rather than unique for each device type in order
to accommodate the iax devices. This is in preparation for fixing the
sub-driver code for idxd. There's no hardware deployment for Sapphire
Rapids platform yet, which means that users have no reason to have
developed scripts against this ABI. There is some exposure to
released versions of accel-config, but those are being fixed up and
an accel-config upgrade is reasonable to get IAX support. As far as
accel-config is concerned IAX support starts when these devices appear
under /sys/bus/dsa, and old accel-config just assumes that an empty /
missing /sys/bus/iax just means a lack of platform support.
Fixes: f25b463883 ("dmaengine: idxd: add IAX configuration support in the IDXD driver")
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161852988298.2203940.4529909758034944428.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The char device setup and cleanup has device lifetime issues regarding when
parts are initialized and cleaned up. The initialization of struct device is
done incorrectly. device_initialize() needs to be called on the 'struct
device' and then additional changes can be added. The ->release() function
needs to be setup via device_type before dev_set_name() to allow proper
cleanup. The change re-parents the cdev under the wq->conf_dev to get
natural reference inheritance. No known dependency on the old device path exists.
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes: 42d279f913 ("dmaengine: idxd: add char driver to expose submission portal to userland")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/161852987721.2203940.1478218825576630810.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Remove devm_* allocation and fix group->conf_dev 'struct device'
lifetime. Address issues flagged by CONFIG_DEBUG_KOBJECT_RELEASE.
Add release functions in order to free the allocated memory at the
group->conf_dev destruction time.
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes: bfe1d56091 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161852987144.2203940.8830315575880047.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Remove devm_* allocation and fix engine->conf_dev 'struct device'
lifetime. Address issues flagged by CONFIG_DEBUG_KOBJECT_RELEASE.
Add release functions in order to free the allocated memory at the
engine conf_dev destruction time.
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes: bfe1d56091 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161852986460.2203940.16603218225412118431.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Remove devm_* allocation and fix wq->conf_dev 'struct device' lifetime.
Address issues flagged by CONFIG_DEBUG_KOBJECT_RELEASE. Add release
functions in order to free the allocated memory for the wq context at
device destruction time.
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes: bfe1d56091 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161852985907.2203940.6840120734115043753.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The devm managed lifetime is incompatible with 'struct device' objects that
resides in idxd context. This is one of the series that clean up the idxd
driver 'struct device' lifetime. Fix idxd->conf_dev 'struct device'
lifetime. Address issues flagged by CONFIG_DEBUG_KOBJECT_RELEASE.
Add release functions in order to free the allocated memory at the
appropriate time.
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes: bfe1d56091 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161852985319.2203940.4650791514462735368.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The devm managed lifetime is incompatible with 'struct device' objects that
resides in idxd context. This is one of the series that clean up the idxd
driver 'struct device' lifetime. Remove devm managed pci interrupt vectors
and replace with unmanged allocators.
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes: bfe1d56091 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/161852983563.2203940.8116028229124776669.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The devm managed lifetime is incompatible with 'struct device' objects that
resides in idxd context. This is one of the series that clean up the idxd
driver 'struct device' lifetime. Remove embedding of dma_device and dma_chan
in idxd since it's not the only interface that idxd will use. The freeing of
the dma_device will be managed by the ->release() function.
Reported-by: Jason Gunthorpe <jgg@nvidia.com>
Fixes: bfe1d56091 ("dmaengine: idxd: Init and probe for Intel data accelerators")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/161852983001.2203940.14817017492384561719.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
A pre-release silicon erratum workaround where wq reset does not clear
WQCFG registers was leaked into upstream code. Use wq reset command
instead of blasting the MMIO region. This also address an issue where
we clobber registers in future devices.
Fixes: da32b28c95 ("dmaengine: idxd: cleanup workqueue config after disabling")
Reported-by: Shreenivaas Devarajan <shreenivaas.devarajan@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161824330020.881560.16375921906426627033.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add disabling/clearing of MSIX permission entries on device shutdown to
mirror the enabling of the MSIX entries on probe. Current code left the
MSIX enabled and the pasid entries still programmed at device shutdown.
Fixes: 8e50d39265 ("dmaengine: idxd: Add shared workqueue support")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/161824457969.882533.6020239898682672311.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add device state check before executing command. Without the check the
command can be issued while device is in halt state and causes the driver to
block while waiting for the completion of the command.
Reported-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Sanjay Kumar <sanjay.k.kumar@intel.com>
Fixes: 0d5c10b4c8 ("dmaengine: idxd: add work queue drain support")
Link: https://lore.kernel.org/r/161219313921.2976211.12222625226450097465.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add support to allow configuration of Intel Analytics Accelerator (IAX) in
addition to the Intel Data Streaming Accelerator (DSA). The IAX hardware
has the same configuration interface as DSA. The main difference
is the type of operations it performs. We can support the DSA and
IAX devices on the same driver with some tweaks.
IAX has a 64B completion record that needs to be 64B aligned, as opposed to
a 32B completion record that is 32B aligned for DSA. IAX also does not
support token management.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/160564555488.1834439.4261958859935360473.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add code to "complete" a descriptor when the descriptor or its completion
address hit a fault error when SVA mode is being used. This error can be
triggered due to bad programming by the user. A lock is introduced in order
to protect the descriptor completion lists since the fault handler will run
from the system work queue after being scheduled in the interrupt handler.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/160382008092.3911367.12766483427643278985.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add shared workqueue support that includes the support of Shared Virtual
memory (SVM) or in similar terms On Demand Paging (ODP). The shared
workqueue uses the enqcmds command in kernel and will respond with retry if
the workqueue is full. Shared workqueue only works when there is PASID
support from the IOMMU.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/160382007499.3911367.26043087963708134.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Export admin command status to sysfs attribute in order to allow user to
retrieve configuration error. Allows user tooling to retrieve the command
error and provide more user friendly error messages.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/159865278770.29455.8026892329182750127.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add sysfs attribute max_batch_size to wq in order to allow the max batch
size configured on a per wq basis. Add support code to configure
the valid user input on wq enable. This is a performance tuning
parameter.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/159865273617.29141.4383066301730821749.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add sysfs attribute max_xfer_size to wq in order to allow the max xfer
size configured on a per wq basis. Add support code to configure
the valid user input on wq enable. This is a performance tuning
parameter.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/159865265404.29141.3049399618578194052.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Switch driver to use MSIX mask and unmask instead of the ignore bit.
When ignore bit is cleared, we must issue an MMIO read to ensure writes
have all arrived and check and process any additional completions. The
ignore bit does not queue up any pending MSIX interrupts. The mask bit
however does. Use API call from interrupt subsystem to mask MSIX
interrupt since the hardware does not have convenient mask bit register.
Suggested-by: Ashok Raj <ashok.raj@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/159319517621.70410.11816465052708900506.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add wq drain support. When a wq is being released, it needs to wait for
all in-flight operation to complete. A device control function
idxd_wq_drain() has been added to facilitate this. A wq drain call
is added to the char dev on release to make sure all user operations are
complete. A wq drain is also added before the wq is being disabled.
A drain command can take an unpredictable period of time. Interrupt support
for device commands is added to allow waiting on the command to
finish. If a previous command is in progress, the new submitter can block
until the current command is finished before proceeding. The interrupt
based submission will submit the command and then wait until a command
completion interrupt happens to complete. All commands are moved to the
interrupt based command submission except for the device reset during
probe, which will be polled.
Fixes: 42d279f913 ("dmaengine: idxd: add char driver to expose submission portal to userland")
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://lore.kernel.org/r/159319502515.69593.13451647706946040301.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
After disabling a device, we should clean up the internal state for
the wqs and zero out the configuration registers. Without doing so can cause
issues when the user reprogram the wqs.
Fixes: c52ca47823 ("dmaengine: idxd: add configuration component of driver")
Reported-by: Yixin Zhang <yixin.zhang@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Yixin Zhang <yixin.zhang@intel.com>
Link: https://lore.kernel.org/r/159311264246.1198.11955791213681679428.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Create a char device region that will allow acquisition of user portals in
order to allow applications to submit DMA operations. A char device will be
created per work queue that gets exposed. The workqueue type "user"
is used to mark a work queue for user char device. For example if the
workqueue 0 of DSA device 0 is marked for char device, then a device node
of /dev/dsa/wq0.0 will be created.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/157965026985.73301.976523230037106742.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Add plumbing for dmaengine subsystem connection. The driver register a DMA
device per DSA device. The channels are dynamically registered when a
workqueue is configured to be "kernel:dmanegine" type.
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/157965026376.73301.13867988830650740445.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The device is left unconfigured when the driver is loaded. Various
components are configured via the driver sysfs attributes. Once
configuration is done, the device can be enabled by writing the device name
to the bind attribute of the device driver sysfs. Disabling can be done
similarly. Also the individual work queues can also be enabled and disabled
through the bind/unbind attributes. A constructed hierarchy is created
through the struct device framework in order to provide appropriate
configuration points and device state and status. This hierarchy is
presented off the virtual DSA bus.
i.e. /sys/bus/dsa/...
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/157965024585.73301.6431413676230150589.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
The idxd driver introduces the Intel Data Stream Accelerator [1] that will
be available on future Intel Xeon CPUs. One of the kernel access
point for the driver is through the dmaengine subsystem. It will initially
provide the DMA copy service to the kernel.
Some of the main functionality introduced with this accelerator
are: shared virtual memory (SVM) support, and descriptor submission using
Intel CPU instructions movdir64b and enqcmds. There will be additional
accelerator devices that share the same driver with variations to
capabilities.
This commit introduces the probe and initialization component of the
driver.
[1]: https://software.intel.com/en-us/download/intel-data-streaming-accelerator-preliminary-architecture-specification
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/157965023991.73301.6186843973135311580.stgit@djiang5-desk3.ch.intel.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
