summaryrefslogtreecommitdiff
path: root/drivers/dma/idxd
AgeCommit message (Collapse)AuthorFilesLines
2020-08-05Merge branch 'for-linus' into fixesVinod Koul8-248/+174
Signed-off-by: Vinod Koul <vkoul@kernel.org> Conflicts: drivers/dma/idxd/sysfs.c
2020-07-13dmaengine: idxd: move idxd interrupt handling to mask instead of ignoreDave Jiang3-46/+13
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>
2020-07-13dmaengine: idxd: add work queue drain supportDave Jiang6-132/+112
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: 42d279f9137a ("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>
2020-07-02dmaengine: idxd: fix misc interrupt handler thread unmaskingDave Jiang1-1/+2
Fix unmasking of misc interrupt handler when completing normal. It exits early and skips the unmasking with the current implementation. Fix to unmask interrupt when exiting normally. Fixes: bfe1d56091c1 ("dmaengine: idxd: Init and probe for Intel data accelerators") Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/159311256528.855.11527922406329728512.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-07-02dmaengine: idxd: cleanup workqueue config after disablingDave Jiang3-0/+31
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: c52ca478233c ("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>
2020-06-24dmaengine: idxd: move submission to sbitmap_queueDave Jiang4-69/+45
Kill the percpu-rwsem for work submission in favor of an sbitmap_queue. 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/159225446631.68253.8860709181621260997.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-06-24dmaengine: idxd: fix cdev locking for open and releaseNikhil Rao1-3/+16
add the wq lock in cdev open and release call. This fixes race conditions observed in the open and close routines. Fixes: 42d279f9137a ("dmaengine: idxd: add char driver to expose submission portal to userland") Signed-off-by: Nikhil Rao <nikhil.rao@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/159285824892.64944.2905413694915141834.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-06-17dmaengine: cookie bypass for out of order completionDave Jiang1-1/+2
The cookie tracking in dmaengine expects all submissions completed in order. Some DMA devices like Intel DSA can complete submissions out of order, especially if configured with a work queue sharing multiple DMA engines. Add a status DMA_OUT_OF_ORDER that tx_status can be returned for those DMA devices. The user should use callbacks to track the completion rather than the DMA cookie. This would address the issue of dmatest complaining that descriptors are "busy" when the cookie count goes backwards due to out of order completion. Add DMA_COMPLETION_NO_ORDER DMA capability to allow the driver to flag the device's ability to complete operations out of order. Reported-by: Swathi Kovvuri <swathi.kovvuri@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Tested-by: Swathi Kovvuri <swathi.kovvuri@intel.com> Link: https://lore.kernel.org/r/158939557151.20335.12404113976045569870.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-06-10Merge tag 'dmaengine-5.8-rc1' of git://git.infradead.org/users/vkoul/slave-dmaLinus Torvalds1-0/+11
Pull dmaengine updates from Vinod Koul: "A fairly small dmaengine update which includes mostly driver updates (dmatest, dw-edma, ioat, mmp-tdma and k3-udma) along with Renesas binding update to json-schema" * tag 'dmaengine-5.8-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (39 commits) dmaengine: imx-sdma: initialize all script addresses dmaengine: ti: k3-udma: Use proper return code in alloc_chan_resources dmaengine: ti: k3-udma: Remove udma_chan.in_ring_cnt dmaengine: ti: k3-udma: Add missing dma_sync call for rx flush descriptor dmaengine: at_xdmac: Replace zero-length array with flexible-array dmaengine: at_hdmac: Replace zero-length array with flexible-array dmaengine: qcom: bam_dma: Replace zero-length array with flexible-array dmaengine: ti: k3-udma: Use PTR_ERR_OR_ZERO() to simplify code dmaengine: moxart-dma: Drop pointless static qualifier in moxart_probe() dmaengine: sf-pdma: Simplify the error handling path in 'sf_pdma_probe()' dmaengine: qcom_hidma: use true,false for bool variable dmaengine: dw-edma: support local dma device transfer semantics dmaengine: Fix doc strings to satisfy validation script dmaengine: Include dmaengine.h into dmaengine.c dmaengine: dmatest: Describe members of struct dmatest_info dmaengine: dmatest: Describe members of struct dmatest_params dmaengine: dmatest: Allow negative timeout value to specify infinite wait Revert "dmaengine: dmatest: timeout value of -1 should specify infinite wait" dmaengine: stm32-dma: direct mode support through device tree dt-bindings: dma: add direct mode support through device tree in stm32-dma ...
2020-05-04dmaengine: idxd: fix interrupt completion after unmaskingDave Jiang2-7/+26
The current implementation may miss completions after we unmask the interrupt. In order to make sure we process all competions, we need to: 1. Do an MMIO read from the device as a barrier to ensure that all PCI writes for completions have arrived. 2. Check for any additional completions that we missed. Fixes: 8f47d1a5e545 ("dmaengine: idxd: connect idxd to dmaengine subsystem") Reported-by: Sanjay Kumar <sanjay.k.kumar@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158834641769.35613.1341160109892008587.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-04-15dmaengine: idxd: export hw version through sysfsDave Jiang1-0/+11
Some user apps would like to know the hardware version in order to determine the variation of the hardware. Export the hardware version number to userspace via sysfs. Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158696714008.39484.13401950732606906479.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-04-03Merge tag 'dmaengine-5.7-rc1' of git://git.infradead.org/users/vkoul/slave-dmaLinus Torvalds3-11/+16
Pull dmaengine updates from Vinod Koul: "Core: - Some code cleanup and optimization in core by Andy - Debugfs support for displaying dmaengine channels by Peter Drivers: - New driver for uniphier-xdmac controller - Updates to stm32 dma, mdma and dmamux drivers and PM support - More updates to idxd drivers - Bunch of changes in tegra-apb driver and cleaning up of pm functions - Bunch of spelling fixes and Replace zero-length array patches - Shutdown hook for fsl-dpaa2-qdma driver - Support for interleaved transfers for ti-edma and virtualization support for k3-dma driver - Support for reset and updates in xilinx_dma driver - Improvements and locking updates in at_hdma driver" * tag 'dmaengine-5.7-rc1' of git://git.infradead.org/users/vkoul/slave-dma: (89 commits) dt-bindings: dma: renesas,usb-dmac: add r8a77961 support dmaengine: uniphier-xdmac: Remove redandant error log for platform_get_irq dmaengine: tegra-apb: Improve DMA synchronization dmaengine: tegra-apb: Don't save/restore IRQ flags in interrupt handler dmaengine: tegra-apb: mark PM functions as __maybe_unused dmaengine: fix spelling mistake "exceds" -> "exceeds" dmaengine: sprd: Set request pending flag when DMA controller is active dmaengine: ppc4xx: Use scnprintf() for avoiding potential buffer overflow dmaengine: idxd: remove global token limit check dmaengine: idxd: reflect shadow copy of traffic class programming dmaengine: idxd: Merge definition of dsa_batch_desc into dsa_hw_desc dmaengine: Create debug directories for DMA devices dmaengine: ti: k3-udma: Implement custom dbg_summary_show for debugfs dmaengine: Add basic debugfs support dmaengine: fsl-dpaa2-qdma: remove set but not used variable 'dpaa2_qdma' dmaengine: ti: edma: fix null dereference because of a typo in pointer name dmaengine: fsl-dpaa2-qdma: Adding shutdown hook dmaengine: uniphier-xdmac: Add UniPhier external DMA controller driver dt-bindings: dmaengine: Add UniPhier external DMA controller bindings dmaengine: ti: k3-udma: Implement support for atype (for virtualization) ...
2020-03-23dmaengine: idxd: fix off by one on cdev dwq refcountDave Jiang1-2/+2
The refcount check for dedicated workqueue (dwq) is off by one and allows more than 1 user to open the char device. Fix check so only a single user can open the device. Fixes: 42d279f9137a ("dmaengine: idxd: add char driver to expose submission portal to userland") Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158403020187.10208.14117394394540710774.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-11dmaengine: idxd: remove global token limit checkDave Jiang1-5/+0
The global token_limit is not tied to group tokens_reserved and tokens_allowed parameters. Remove the check in order to allow independent configuration. Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Reported-by: Yixin Zhang <yixin.zhang@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158386266911.11066.7545764533072221536.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-11dmaengine: idxd: reflect shadow copy of traffic class programmingDave Jiang1-2/+2
The traffic class are set to -1 at initialization until the user programs them. If the user choose not to, the driver will program appropriate defaults. The driver also needs to update the shadowed copies of the values after doing the programming. Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Reported-by: Yixin Zhang <yixin.zhang@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158386263076.10898.4586509576813094559.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-02dmaengine: idxd: expose general capabilities register in sysfsDave Jiang1-0/+11
There are some capabilities for the device that are interesting to user apps that are interacting directly with the device. Expose gencap register in sysfs to allow that information. Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158256729399.55526.10842505054968710547.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-03-02dmaengine: idxd: check return result from check_vma() in cdevDave Jiang1-0/+2
The returned result from the check_vma() function in the cdev ->mmap() call needs to be handled. Add the check and returning error. Fixes: 42d279f9137a ("dmaengine: idxd: add char driver to expose submission portal to userland") Reported-by: Vinod Koul <vkoul@kernel.org> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158264926659.9387.14325163515683047959.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-24dmaengine: idxd: wq size configuration needs to check global max sizeDave Jiang1-1/+15
The current size_store() function for idxd sysfs does not check the total wq size. This allows configuration of all wqs with total wq size. Add check to make sure the wq sysfs attribute rejects storing of size over the total wq size. Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Reported-by: Jerry Chen <jerry.t.chen@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158213309629.2509.3583411832507185041.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-24dmaengine: idxd: sysfs input of wq incorrect wq type should return errorDave Jiang1-2/+4
Currently when inputing an unrecognized wq type, we set the wq type to "none". It really should return error and not change the existing wq type that's in the kernel. Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Reported-by: Yixin Zhang <yixin.zhang@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158213304803.2290.13336343633425868211.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-19dmaengine: idxd: correct reserved token calculationDave Jiang1-1/+1
The calcuation for limit of reserved token did not take into account the change the user wanted vs the current group reserved token. This causes changing of the reserved token to be possible only after we set the value of the reserved token back to 0. Fix calculation so we can set a value that is non zero for reserved token. Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Reported-by: Jerry Chen <jerry.t.chen@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158204471889.37789.7749177228265869168.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-13dmaengine: idxd: Fix error handling in idxd_wq_cdev_dev_setup()Dan Carpenter1-2/+2
We can't call kfree(dev) after calling device_register(dev). The "dev" pointer has to be freed using put_device(). Fixes: 42d279f9137a ("dmaengine: idxd: add char driver to expose submission portal to userland") Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Acked-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/20200205123248.hmtog7qa2eiqaagh@kili.mountain Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-13dmaengine: idxd: fix runaway module ref count on device driver bindDave Jiang1-0/+3
idxd_config_bus_probe() calls try_module_get() but never calls module_put() when it fails. Thus with every failed attempt, the ref count goes up. Add module_put() in failure paths. Fixes: c52ca478233c ("dmaengine: idxd: add configuration component of driver") Reported-by: Jerry Chen <jerry.t.chen@intel.com> Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/158144296730.41381.12134210685456322434.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-13dmaengine: idxd: remove set but not used variable 'idxd_cdev'YueHaibing1-2/+0
drivers/dma/idxd/cdev.c: In function idxd_cdev_open: drivers/dma/idxd/cdev.c:77:20: warning: variable idxd_cdev set but not used [-Wunused-but-set-variable] commit 42d279f9137a ("dmaengine: idxd: add char driver to expose submission portal to userland") involed this. Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: YueHaibing <yuehaibing@huawei.com> Acked-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/20200210151855.55044-1-yuehaibing@huawei.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-02-13dmaengine: idxd: remove set but not used variable 'group'YueHaibing1-2/+1
drivers/dma/idxd/sysfs.c: In function engine_group_id_store: drivers/dma/idxd/sysfs.c:419:29: warning: variable group set but not used [-Wunused-but-set-variable] It is not used, so remove it. Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: YueHaibing <yuehaibing@huawei.com> Acked-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/20200211135335.55924-1-yuehaibing@huawei.com Signed-Off-By: Vinod Koul <vkoul@kernel.org>
2020-02-03dmaengine: idxd: fix boolconv.cocci warningskbuild test robot1-1/+1
Remove unneeded conversion to bool Generated by: scripts/coccinelle/misc/boolconv.cocci CC: Dave Jiang <dave.jiang@intel.com> Signed-off-by: kbuild test robot <lkp@intel.com> Signed-off-by: Julia Lawall <julia.lawall@inria.fr> Acked-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/alpine.DEB.2.21.2001301543150.7476@hadrien Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-01-24dmaengine: idxd: add char driver to expose submission portal to userlandDave Jiang8-5/+422
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>
2020-01-24dmaengine: idxd: connect idxd to dmaengine subsystemDave Jiang8-2/+391
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>
2020-01-24dmaengine: idxd: add descriptor manipulation routinesDave Jiang3-1/+102
This commit adds helper functions for DSA descriptor allocation, submission, and free operations. Signed-off-by: Dave Jiang <dave.jiang@intel.com> Link: https://lore.kernel.org/r/157965025757.73301.12692876585357550065.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Vinod Koul <vkoul@kernel.org>
2020-01-24dmaengine: idxd: add configuration component of driverDave Jiang6-3/+1536
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>
2020-01-24dmaengine: idxd: Init and probe for Intel data acceleratorsDave Jiang6-0/+1843
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>
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-28 20:10:21 +0300