- 24 Jul, 2020 20 commits
-
-
Ofir Bitton authored
We identified a possible race during job completion when working with a single multi-threaded work queue. In order to overcome this race we suggest using a single threaded work queue per completion queue, hence we guarantee jobs completion in order. Signed-off-by:
Ofir Bitton <obitton@habana.ai> Reviewed-by:
Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by:
-
Oded Gabbay authored
Currently the driver halts the device CPU in the halt engines function, which halts all the engines of the ASIC. The problem is that if later on we stop the reset process (due to inability to clean memory mappings in time), the CPU will remain in halt mode. This creates many issues, such as thermal/power control and FLR handling. Therefore, move the halting of the device CPU to the very end of the reset process, just before writing to the registers to initiate the reset. In addition, the driver now needs to send a message to the device F/W to disable it from sending interrupts to the host machine because during halt engines function the driver disables the MSI/MSI-X interrupts. Signed-off-by:
Tomer Tayar <ttayar@habana.ai>
-
Omer Shpigelman authored
Remove an old hash that is not in use anymore. Signed-off-by:
Omer Shpigelman <oshpigelman@habana.ai> Reviewed-by:
-
Ofir Bitton authored
Instead of using the free slots amount on the compute CQ to determine whether we can submit work to queues, use the queues pi/ci. This is needed in future ASICs where we don't have CQ per queue. Signed-off-by:
-
Ofir Bitton authored
Currently the amount of maximum queues is statically configured. Using a static value is causing redundunt cycles when traversing all queues and consumes more memory than actually needed. In this patch we configure each asic with the exact number of queues needed. Signed-off-by:
-
Oded Gabbay authored
Soft-reset isn't supported in GAUDI. Remove the code that performs it and print error in case the user wants to do it via sysfs. Signed-off-by:
-
Ofir Bitton authored
Divide iATU initialization into inbound/outbound methods. We must separate it in order to enable different match mode per PCIe region. In addition, added support for PCI address match mode. Signed-off-by:
-
Oded Gabbay authored
ECC (Error Correcting Code) interrupts are going to be handled by the FW. Hence, we define an interface in which the driver can obtain the relevant ECC information. This information is needed for monitoring and can also lead to a hard reset if ECC error is not correctable. Signed-off-by:
-
Ofir Bitton authored
Add command submission statistics structure which can be obtained through the info ioctl. Each drop counter describes the reason for which the command submission was dropped. This information is needed for the user to be aware of the specific reason for which the submitted work was dropped. The user can then utilize the driver more efficiently. Signed-off-by:
-
Christine Gharzuzi authored
Extract detection of the cpu boot status to a function to allow code reuse Signed-off-by:
Christine Gharzuzi <cgharzuzi@habana.ai> Reviewed-by:
-
Oded Gabbay authored
rephrase some error/warning/notice messages to make them more accessible to ordinary users. There is no need to print context ASID as the driver currently doesn't support multiple contexts. Signed-off-by:
-
Ofir Bitton authored
After recent concurrent cs amount increase, we must also increase queues depth since much more concurrent work can be done. All external queue depths were increased to 4096 as gaudi's internal queue depths were also increased to 1024. Signed-off-by:
-
Omer Shpigelman authored
Rephrase F/W error message to make it more understandable to ordinary users. Signed-off-by:
-
Adam Aharon authored
The profiler needs to know the PLL values for correctly showing the profiling data. Because our firmware can use different PLL configurations, we need to read the PLL values from the ASIC to pass them to the profiler. Signed-off-by:
Adam Aharon <aaharon@habana.ai> Reviewed-by:
-
Oded Gabbay authored
Once there is a 64-bit field in a structure, GCC compiler for ARM aligns the structure to 8 bytes. In order to avoid confusion when these structures are being passed between CPUs from different architectures, we explicitly align the structure to 8 bytes. Reviewed-by:
-
Oded Gabbay authored
MAP/UNMAP are done also for device memory. Reviewed-by:
-
Ofir Bitton authored
Use proper bitfield masks instead of shifting values when configuring packets sent to device. Signed-off-by:
-
Ofir Bitton authored
Currently sync stream is limited only for external queues. We want to remove this constraint by adding a new queue property dedicated for sync stream. In addition we move the initialization and reset methods to the common code since we can re-use them with slight changes. Signed-off-by:
-
Ofir Bitton authored
Training schemes requires much more concurrent command submissions than inference does. In addition, training command submissions can be completed in a non serialized manner. Hence, we add support in which each ASIC will be able to configure the amount of concurrent pending command submissions, rather than use a predefined amount. This change will enhance performance by allowing the user to add more concurrent work without waiting for the previous work to be completed. Signed-off-by:
-
Oded Gabbay authored
We no longer need to initialize the rate limiters in GAUDI A1. Reviewed-by:
-
- 23 Jul, 2020 20 commits
-
-
Tomas Winkler authored
Replace the single element arrays with a simple value type u8 reserved, even thought is is not used for dynamically sized trailing elements it confuses the effort of replacing one-element arrays with flexible arrays for that purpose. Link: https://github.com/KSPP/linux/issues/79 Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Reviewed-by:
Gustavo A. R. Silva <gustavoars@kernel.org> Signed-off-by:
Tomas Winkler <tomas.winkler@intel.com> Link: https://lore.kernel.org/r/20200723145927.882743-7-tomas.winkler@intel.comSigned-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Tomas Winkler authored
Use sizeof(*dev) + sizeof(*hw) instead of sizeof(struct mei_device) + sizeof(struct mei_me_hw) There is a possibility of bug when variable type has changed but corresponding struct passed to the sizeof has not. Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Reviewed-by:
-
Tomas Winkler authored
There is a possibility of bug when variable type has changed but corresponding struct passed to the sizeof has not. Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Reviewed-by:
-
Tomas Winkler authored
There is a possibility of bug when variable type has changed but corresponding struct passed to the sizeof has not. Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Reviewed-by:
-
Tomas Winkler authored
Use sizeof(connect_data))) instead of sizeof(struct mei_connect_client_data) when copying data between user space and kernel. There is a possibility of bug when variable type has changed but corresponding struct passed to the sizeof has not. Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Reviewed-by:
-
Tomas Winkler authored
There is a possibility of bug when variable type has changed but corresponding struct passed to the sizeof has not. Reviewed-by:
-
Greg Kroah-Hartman authored
This reverts commit 3c3b7dde, as it turns out Tomas made a better series of patches for this same issue. Cc: Gustavo A. R. Silva <gustavoars@kernel.org> Cc: Tomas Winkler <tomas.winkler@intel.com> Signed-off-by:
-
Grigore Popescu authored
Because the DPNIs are probed before DPMCPs and other objects that need to be allocated, messages like "No more resources of type X left" are printed by the fsl-mc bus driver. This patch resolves the issue by probing the allocatable objects first and then any other object that may use them. Signed-off-by:
Grigore Popescu <grigore.popescu@nxp.com> Signed-off-by:
Ioana Ciornei <ioana.ciornei@nxp.com> Reviewed-by:
Laurentiu Tudor <laurentiu.tudor@nxp.com> Link: https://lore.kernel.org/r/20200717154800.17169-4-ioana.ciornei@nxp.comSigned-off-by:
-
Laurentiu Tudor authored
Replace the spinlock that serializes the MC commands with a raw spinlock. This is needed for the RT kernel because there are MC commands sent in interrupt context. Signed-off-by:
-
Ioana Ciornei authored
The MC bus has different types of devices that can be discovered on the bus. Add the missing device types. Signed-off-by:
-
Vaibhav Gupta authored
Drivers should not use legacy power management as they have to manage power states and related operations, for the device, themselves. This driver was handling them with the help of PCI helper functions like pci_save/restore_state(), pci_enable/disable_device(), etc. With generic PM, all essentials will be handled by the PCI core. Driver needs to do only device-specific operations. The driver was also using pci_enable_wake(...,..., 0) to disable wake. Use device_wakeup_disable() instead. Compile-tested only. Signed-off-by:
Vaibhav Gupta <vaibhavgupta40@gmail.com> Link: https://lore.kernel.org/r/20200720101722.145211-1-vaibhavgupta40@gmail.comSigned-off-by:
-
Christophe JAILLET authored
Avoid a memset after a call to 'dma_alloc_coherent()'. This is useless since commit 518a2f19 ("dma-mapping: zero memory returned from dma_alloc_*") Signed-off-by:
Christophe JAILLET <christophe.jaillet@wanadoo.fr> Link: https://lore.kernel.org/r/20200718070246.338016-1-christophe.jaillet@wanadoo.frSigned-off-by:
-
Christophe JAILLET authored
The wrappers in include/linux/pci-dma-compat.h should go away. The patch has been generated with the coccinelle script below and has been hand modified to replace GFP_ with a correct flag. It has been compile tested. When memory is allocated in 'ilo_ccb_setup()' GFP_ATOMIC must be used because a spin_lock is hold in 'ilo_open()' before calling 'ilo_ccb_setup()' @@ @@ - PCI_DMA_BIDIRECTIONAL + DMA_BIDIRECTIONAL @@ @@ - PCI_DMA_TODEVICE + DMA_TO_DEVICE @@ @@ - PCI_DMA_FROMDEVICE + DMA_FROM_DEVICE @@ @@ - PCI_DMA_NONE + DMA_NONE @@ expression e1, e2, e3; @@ - pci_alloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_) @@ expression e1, e2, e3; @@ - pci_zalloc_consistent(e1, e2, e3) + dma_alloc_coherent(&e1->dev, e2, e3, GFP_) @@ expression e1, e2, e3, e4; @@ - pci_free_consistent(e1, e2, e3, e4) + dma_free_coherent(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_map_single(e1, e2, e3, e4) + dma_map_single(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_unmap_single(e1, e2, e3, e4) + dma_unmap_single(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4, e5; @@ - pci_map_page(e1, e2, e3, e4, e5) + dma_map_page(&e1->dev, e2, e3, e4, e5) @@ expression e1, e2, e3, e4; @@ - pci_unmap_page(e1, e2, e3, e4) + dma_unmap_page(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_map_sg(e1, e2, e3, e4) + dma_map_sg(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_unmap_sg(e1, e2, e3, e4) + dma_unmap_sg(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_cpu(e1, e2, e3, e4) + dma_sync_single_for_cpu(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_single_for_device(e1, e2, e3, e4) + dma_sync_single_for_device(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_cpu(e1, e2, e3, e4) + dma_sync_sg_for_cpu(&e1->dev, e2, e3, e4) @@ expression e1, e2, e3, e4; @@ - pci_dma_sync_sg_for_device(e1, e2, e3, e4) + dma_sync_sg_for_device(&e1->dev, e2, e3, e4) @@ expression e1, e2; @@ - pci_dma_mapping_error(e1, e2) + dma_mapping_error(&e1->dev, e2) @@ expression e1, e2; @@ - pci_set_dma_mask(e1, e2) + dma_set_mask(&e1->dev, e2) @@ expression e1, e2; @@ - pci_set_consistent_dma_mask(e1, e2) + dma_set_coherent_mask(&e1->dev, e2) Signed-off-by:
-
Greg Kroah-Hartman authored
Merge tag 'phy-for-5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy into char-misc-next Vinod writes: phy for 5.9 - New PHY Drivers: - Samsung UFS - Qcom USB DWC for ipq806x - Xilinx ZynqMP Gigabit Transceiver - Qcom USB QMP for IPQ8074 - BCM63xx USBH - Removed: - Qcom ufs qmp phy driver - Updates: - Support for Qcom SM8250 QMP V4 USB3 UNIPHY - qcom-snps runtime pm support - Cleanup of W=1 warns in the subsystem * tag 'phy-for-5.9' of git://git.kernel.org/pub/scm/linux/kernel/git/phy/linux-phy: (46 commits) phy: qualcomm: fix setting of tx_deamp_3_5db when device property read fails phy: bcm63xx-usbh: Add BCM63xx USBH driver dt-bindings: phy: add bcm63xx-usbh bindings phy: armada-38x: fix NETA lockup when repeatedly switching speeds dt: update Marvell Armada 38x COMPHY binding phy: samsung-ufs: Fix IS_ERR argument dt-bindings: phy: renesas,usb3-phy: Add r8a774e1 support dt-bindings: phy: renesas,usb2-phy: Add r8a774e1 support phy: renesas: rcar-gen3-usb2: exit if request_irq() failed phy: renesas: rcar-gen3-usb2: move irq registration to init devicetree: bindings: phy: Document ipq806x dwc3 qcom phy phy: qualcomm: add qcom ipq806x dwc usb phy driver phy: samsung-ufs: add UFS PHY driver for samsung SoC dt-bindings: phy: Document Samsung UFS PHY bindings phy: sun4i-usb: explicitly include gpio/consumer.h phy: stm32: use NULL instead of zero phy: exynos5-usbdrd: use correct format for structure description phy: rockchip-typec: use correct format for structure description phy: xgene: remove unsigned integer comparison with less than zero phy: mapphone-mdm6600: Add missing description for some structure fields ...
-
Alexander A. Klimov authored
Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by:Alexander A. Klimov <grandmaster@al2klimov.de> Link: https://lore.kernel.org/r/20200713104453.33414-1-grandmaster@al2klimov.deSigned-off-by:
-
Alexander A. Klimov authored
Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by: -
Randy Dunlap authored
Drop the repeated word "the" in a comment. Cc: Arve Hjønnevåg <arve@android.com> Cc: Todd Kjos <tkjos@android.com> Cc: Martijn Coenen <maco@android.com> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Hridya Valsaraju <hridya@google.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: devel@driverdev.osuosl.org Acked-by:
Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by:
Randy Dunlap <rdunlap@infradead.org> Link: https://lore.kernel.org/r/20200719002738.20210-1-rdunlap@infradead.orgSigned-off-by:
-
Randy Dunlap authored
Drop the repeated word "the" in a comment. Signed-off-by:
-
Gustavo A. R. Silva authored
One-element arrays are being deprecated[1]. Replace the one-element arrays with a simple value type u8 reserved, once this is just a placeholder for alignment. Also, while there, use the preferred form for passing a size of a struct. The alternative form where struct name is spelled out hurts readability and introduces an opportunity for a bug when the variable type is changed but the corresponding sizeof that is passed as argument is not. [1] https://github.com/KSPP/linux/issues/79Signed-off-by:
-
Alexander A. Klimov authored
Rationale: Reduces attack surface on kernel devs opening the links for MITM as HTTPS traffic is much harder to manipulate. Deterministic algorithm: For each file: If not .svg: For each line: If doesn't contain `\bxmlns\b`: For each link, `\bhttp://[^# \t\r\n]*(?:\w|/)`: If neither `\bgnu\.org/license`, nor `\bmozilla\.org/MPL\b`: If both the HTTP and HTTPS versions return 200 OK and serve the same content: Replace HTTP with HTTPS. Signed-off-by:
-
