summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2020-09-22habanalabs/gaudi: increase timeout for boot fit loadOded Gabbay
The firmware running in the boot stage takes more time to execute due to increased security mechanisms. Therefore, we need to increase the timeout we wait for the boot fit to finish loading. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: add debugfs support for MMU with 6 HOPsMoti Haimovski
This commit modify the existing debugfs code to support future devices that have a 6 HOPs MMU implementation instead of 5 HOPs implementation. Signed-off-by: Moti Haimovski <mhaimovski@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: add num_hops to hl_mmu_propertiesMoti Haimovski
This commit adds the number of HOPs supported by the device to the device MMU properties. Signed-off-by: Moti Haimovski <mhaimovski@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: refactor MMU as device-orientedMoti Haimovski
As preparation to MMU v2, rework MMU to be device oriented instantiated according to the device in hand. Signed-off-by: Moti Haimovski <mhaimovski@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: rename mmu.c to mmu_v1.cMoti Haimovski
In the future we will have MMU v2 code, so we need to prepare the driver for it. The first step is to rename the current MMU file to mmu_v1.c. Signed-off-by: Moti Haimovski <mhaimovski@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: use smallest possible alignment for virtual addressesOmer Shpigelman
Change the acquiring of a device virtual address for mapping by using the smallest possible alignment, rather than the biggest, depending on the page size used by the user for allocating the memory. This will lower the virtual space memory consumption. Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: check flag before reset because of f/w eventOded Gabbay
For consistency with GAUDI code, add check of the relevant flag in the device structure before resetting the GOYA device in case of firmware event. Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: increase PQ COMP_OFFSET by one nibbleOded Gabbay
For future ASICs, we increase this field by one nibble. This field was not used by the current ASICs so this change doesn't break anything. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: Fix alignment issue in cpucp_info structureOfir Bitton
Because the device CPU compiler aligns structures to 8 bytes, struct cpucp_info has an alignment issue as some parts in the structure are not aligned to 8 bytes. It is preferred that we explicitly insert placeholders inside the structure to avoid confusion in order to validate this scenario, we printed both pointers: __u8 cpucp_version[VERSION_MAX_LEN]; (0xffff899c67ed4cbc) __le64 dram_size; (0xffff899c67ed4d40) we see difference of 132 bytes although the first array is only 128 bytes long, Meaning compiler added a 4 byte padding. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: remove unused defineOded Gabbay
Cleanup the code. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: remove unused ASIC function pointerOded Gabbay
Old function pointer that was left when the call to this function pointer was removed. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: rename ArmCP to CPU-CPOded Gabbay
There were a couple of comments where the name ArmCP was still used. Rename it to CPU-CP. In addition, rename ArmCP or ARM in log messages to "device CPU". Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: count dropped CS because max CS in-flightOded Gabbay
There is a case where the user reaches the maximum number of CS in-flight. In that case, the driver rejects the new CS of the user with EAGAIN. Count that event so the user can query the driver later to see if it happened. Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: make use of dma_mmap_coherentHillf Danton
Add dma_mmap_coherent() for goya and gaudi to match their use of dma_alloc_coherent(), see the Link tag for why. Link: https://lore.kernel.org/lkml/20200609091727.GA23814@lst.de/ Cc: Christoph Hellwig <hch@lst.de> Cc: Zhang Li <li.zhang@bitmain.com> Cc: Ding Z Nan <oshack@hotmail.com> Signed-off-by: Hillf Danton <hdanton@sina.com> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: clear vm_pgoff before doing the mmapOded Gabbay
The driver use vm_pgoff to hold the CB idr handle. Before we actually call the mapping function, we need to clear the handle so there won't be any garbage left in vm_pgoff. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: restructure hl_mmapOded Gabbay
Arrange the hl_mmap code to be more structured and expandable for the future. Add better defines that describe our usage of the vm_pgoff. Note that I shamelessly took the code and defines from the amdkfd driver (my previous driver). Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: cast to u64 before shift > 31 bitsOded Gabbay
When shifting a boolean variable by more than 31 bits and putting the result into a u64 variable, we need to cast the boolean into unsigned 64 bits to prevent possible overflow. Reported-by: kernel test robot <lkp@intel.com> Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: replace armcp with the generic cpucpOded Gabbay
ArmCP mandates that the device CPU is always an ARM processor, which might be wrong in the future. Most of this change is an internal renaming of variables, functions and defines but there are two entries in sysfs which have armcp in their names. Add identical cpucp entries but don't remove yet the armcp entries. Those will be deprecated next year. Add the documentation about it in sysfs documentation. Signed-off-by: Moti Haimovski <mhaimovski@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: update GAUDI hardware specsOded Gabbay
Add define for the 2 MME slave engines. Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: add support for getting device total energyfarah kassabri
Add driver implementation for reading the total energy consumption from the device ARM FW. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: Include linux/bitfield.h only in habanalabs.hTomer Tayar
Include linux/bitfield.h only in habanalabs.h, instead of in each and every file that needs it, as habanalabs.h is already included by all. Signed-off-by: Tomer Tayar <ttayar@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: extend busy engines mask to 64 bitsfarah kassabri
change busy engines bitmask to 64 bits in order to represent more engines, needed for future ASIC support. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: use 1U when shifting bitsOded Gabbay
Eliminate following warning: warning: Shifting signed 32-bit value by 31 bits is undefined behavior Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: check TPC vector pipe is emptyOded Gabbay
The driver waits for the TPC vector pipe to be empty before checking if the TPC kernel has finished executing, but the code doesn't validate that the pipe was indeed empty, it just wait for it without checking the return value. Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: remove redundant assignment to variableOded Gabbay
new_dma_pkt->ctl is assigned a value and then is reassigned a new value without the first value ever being used. Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: use FIELD_PREP() instead of <<Oded Gabbay
Use the standard FIELD_PREP() macro instead of << operator to perform bitmask operations. This ensures type check safety and eliminate compiler warnings. Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: use standard BIT() and GENMASK()Oded Gabbay
Use the standard macros to define bitmasks. Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: eliminate redundant else conditionOded Gabbay
If both parts of if-else are goto statements, we can remove the else and put the else goto statement after the if statement. Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: cast int to u32 before printing it with %uOded Gabbay
%u is used for unsigned so we need to cast the int variable to u32 to avoid compiler warning. Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: change CB's ID to be 64 bitsOded Gabbay
Although the possible values for CB's ID are only 32 bits, there are a few places in the code where this field is shifted and passed into a function which expects 64 bits. Reported-by: kernel test robot <lkp@intel.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: print the queue id in case of an errorDotan Barak
If there is a failure during the testing of a queue, to ease up debugging - print the queue id. Signed-off-by: Dotan Barak <dbarak@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: remove security from ARB_MST_QUIET registerfarah kassabri
Allow user application to write to this register in order to be able to configure the quiet period of the QMAN between grants. Signed-off-by: farah kassabri <fkassabri@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: PCIe Advanced Error Reporting supportOfir Bitton
driver will now get notified upon any PCI error occurred and will respond according to the severity of the error. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: expose sync manager resources allocation in INFO IOCTLOfir Bitton
Although the driver defines the first user-available sync manager object and monitor in habanalabs.h, we would like to also expose this information via the INFO IOCTL so the runtime can get this information dynamically. This is because in future ASICs we won't need to define it statically. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: add information about PCIe controllerOfir Bitton
Update firmware header with new API for getting pcie info such as tx/rx throughput and replay counter. These counters are needed by customers for monitor and maintenance of multiple devices. Add new opcodes to the INFO ioctl to retrieve these counters. Signed-off-by: Ofir Bitton <obitton@habana.ai> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: Replace dma-fence mechanism with completionsOfir Bitton
habanalabs driver uses dma-fence mechanism for synchronization. dma-fence mechanism was designed solely for GPUs, hence we purpose a simpler mechanism based on completions to replace current dma-fence objects. Signed-off-by: Ofir Bitton <obitton@habana.ai> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
2020-09-22habanalabs: increase length of ASIC nameOded Gabbay
Future ASIC names are longer than 15 chars so increase the variable length to 32 chars. Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com> Reviewed-by: Tomer Tayar <ttayar@habana.ai>
2020-09-22MAINTAINERS: Add entry for the Nitro Enclaves driverAndra Paraschiv
Add entry in the MAINTAINERS file for the Nitro Enclaves files such as the documentation, the header files, the driver itself and the user space sample. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Update the location of the documentation, as it has been moved to the "virt" directory. v7 -> v8 * No changes. v6 -> v7 * No changes. v5 -> v6 * No changes. v4 -> v5 * No changes. v3 -> v4 * No changes. v2 -> v3 * Update file entries to be in alphabetical order. v1 -> v2 * No changes. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-19-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add overview documentationAndra Paraschiv
Add documentation on the overview of Nitro Enclaves. Include it in the virtualization specific directory. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Move the Nitro Enclaves documentation to the "virt" directory and add an entry for it in the corresponding index file. v7 -> v8 * Add info about the primary / parent VM CID value. * Update reference link for huge pages. * Add reference link for the x86 boot protocol. * Add license mention and update doc title / chapter formatting. v6 -> v7 * No changes. v5 -> v6 * No changes. v4 -> v5 * No changes. v3 -> v4 * Update doc type from .txt to .rst. * Update documentation based on the changes from v4. v2 -> v3 * No changes. v1 -> v2 * New in v2. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-18-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add sample for ioctl interface usageAndra Paraschiv
Add a user space sample for the usage of the ioctl interface provided by the Nitro Enclaves driver. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * No changes. v7 -> v8 * Track NE custom error codes for invalid page size, invalid flags and enclave CID. * Update the heartbeat logic to have a listener fd first, then start the enclave and then accept connection to get the heartbeat. * Update the reference link to the hugetlb documentation. v6 -> v7 * Track POLLNVAL as poll event in addition to POLLHUP. v5 -> v6 * Remove "rc" mentioning when printing errno string. * Remove the ioctl to query API version. * Include usage info for NUMA-aware hugetlb configuration. * Update documentation to kernel-doc format. * Add logic for enclave image loading. v4 -> v5 * Print enclave vCPU ids when they are created. * Update logic to map the modified vCPU ioctl call. * Add check for the path to the enclave image to be less than PATH_MAX. * Update the ioctl calls error checking logic to match the NE specific error codes. v3 -> v4 * Update usage details to match the updates in v4. * Update NE ioctl interface usage. v2 -> v3 * Remove the include directory to use the uapi from the kernel. * Remove the GPL additional wording as SPDX-License-Identifier is already in place. v1 -> v2 * New in v2. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Alexandru Vasile <lexnv@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-17-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add Makefile for the Nitro Enclaves driverAndra Paraschiv
Add Makefile for the Nitro Enclaves driver, considering the option set in the kernel config. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Remove -Wall flags, could use W=1 as an option for this. v7 -> v8 * No changes. v6 -> v7 * No changes. v5 -> v6 * No changes. v4 -> v5 * No changes. v3 -> v4 * No changes. v2 -> v3 * Remove the GPL additional wording as SPDX-License-Identifier is already in place. v1 -> v2 * Update path to Makefile to match the drivers/virt/nitro_enclaves directory. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-16-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add Kconfig for the Nitro Enclaves driverAndra Paraschiv
Add kernel config entry for Nitro Enclaves, including dependencies. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * No changes. v7 -> v8 * No changes. v6 -> v7 * Remove, for now, the dependency on ARM64 arch. x86 is currently supported, with Arm to come afterwards. The NE kernel driver can be built for aarch64 arch. v5 -> v6 * No changes. v4 -> v5 * Add arch dependency for Arm / x86. v3 -> v4 * Add PCI and SMP dependencies. v2 -> v3 * Remove the GPL additional wording as SPDX-License-Identifier is already in place. v1 -> v2 * Update path to Kconfig to match the drivers/virt/nitro_enclaves directory. * Update help in Kconfig. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-15-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add logic for terminating an enclaveAndra Paraschiv
An enclave is associated with an fd that is returned after the enclave creation logic is completed. This enclave fd is further used to setup enclave resources. Once the enclave needs to be terminated, the enclave fd is closed. Add logic for enclave termination, that is mapped to the enclave fd release callback. Free the internal enclave info used for bookkeeping. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Use the ne_devs data structure to get the refs for the NE PCI device. v7 -> v8 * No changes. v6 -> v7 * Remove the pci_dev_put() call as the NE misc device parent field is used now to get the NE PCI device. * Update the naming and add more comments to make more clear the logic of handling full CPU cores and dedicating them to the enclave. v5 -> v6 * Update documentation to kernel-doc format. * Use directly put_page() instead of unpin_user_pages(), to match the get_user_pages() calls. v4 -> v5 * Release the reference to the NE PCI device on enclave fd release. * Adapt the logic to cpumask enclave vCPU ids and CPU cores. * Remove sanity checks for situations that shouldn't happen, only if buggy system or broken logic at all. v3 -> v4 * Use dev_err instead of custom NE log pattern. v2 -> v3 * Remove the WARN_ON calls. * Update static calls sanity checks. * Update kzfree() calls to kfree(). v1 -> v2 * Add log pattern for NE. * Remove the BUG_ON calls. * Update goto labels to match their purpose. * Add early exit in release() if there was a slot alloc error in the fd creation path. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Alexandru Vasile <lexnv@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-14-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add logic for starting an enclaveAndra Paraschiv
After all the enclave resources are set, the enclave is ready for beginning to run. Add ioctl command logic for starting an enclave after all its resources, memory regions and CPUs, have been set. The enclave start information includes the local channel addressing - vsock CID - and the flags associated with the enclave. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Use the ne_devs data structure to get the refs for the NE PCI device. v7 -> v8 * Add check for invalid enclave CID value e.g. well-known CIDs and parent VM CID. * Add custom error code for incorrect flag in enclave start info and invalid enclave CID. v6 -> v7 * Update the naming and add more comments to make more clear the logic of handling full CPU cores and dedicating them to the enclave. v5 -> v6 * Check for invalid enclave start flags. * Update documentation to kernel-doc format. v4 -> v5 * Add early exit on enclave start ioctl function call error. * Move sanity checks in the enclave start ioctl function, outside of the switch-case block. * Remove log on copy_from_user() / copy_to_user() failure. v3 -> v4 * Use dev_err instead of custom NE log pattern. * Update the naming for the ioctl command from metadata to info. * Check for minimum enclave memory size. v2 -> v3 * Remove the WARN_ON calls. * Update static calls sanity checks. v1 -> v2 * Add log pattern for NE. * Check if enclave state is init when starting an enclave. * Remove the BUG_ON calls. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Alexandru Vasile <lexnv@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-13-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add logic for setting an enclave memory regionAndra Paraschiv
Another resource that is being set for an enclave is memory. User space memory regions, that need to be backed by contiguous memory regions, are associated with the enclave. One solution for allocating / reserving contiguous memory regions, that is used for integration, is hugetlbfs. The user space process that is associated with the enclave passes to the driver these memory regions. The enclave memory regions need to be from the same NUMA node as the enclave CPUs. Add ioctl command logic for setting user space memory region for an enclave. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Use the ne_devs data structure to get the refs for the NE PCI device. v7 -> v8 * Add early check, while getting user pages, to be multiple of 2 MiB for the pages that back the user space memory region. * Add custom error code for incorrect user space memory region flag. * Include in a separate function the sanity checks for each page of the user space memory region. v6 -> v7 * Update check for duplicate user space memory regions to cover additional possible scenarios. v5 -> v6 * Check for max number of pages allocated for the internal data structure for pages. * Check for invalid memory region flags. * Check for aligned physical memory regions. * Update documentation to kernel-doc format. * Check for duplicate user space memory regions. * Use directly put_page() instead of unpin_user_pages(), to match the get_user_pages() calls. v4 -> v5 * Add early exit on set memory region ioctl function call error. * Remove log on copy_from_user() failure. * Exit without unpinning the pages on NE PCI dev request failure as memory regions from the user space range may have already been added. * Add check for the memory region user space address to be 2 MiB aligned. * Update logic to not have a hardcoded check for 2 MiB memory regions. v3 -> v4 * Check enclave memory regions are from the same NUMA node as the enclave CPUs. * Use dev_err instead of custom NE log pattern. * Update the NE ioctl call to match the decoupling from the KVM API. v2 -> v3 * Remove the WARN_ON calls. * Update static calls sanity checks. * Update kzfree() calls to kfree(). v1 -> v2 * Add log pattern for NE. * Update goto labels to match their purpose. * Remove the BUG_ON calls. * Check if enclave max memory regions is reached when setting an enclave memory region. * Check if enclave state is init when setting an enclave memory region. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Alexandru Vasile <lexnv@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-12-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add logic for getting the enclave image load infoAndra Paraschiv
Before setting the memory regions for the enclave, the enclave image needs to be placed in memory. After the memory regions are set, this memory cannot be used anymore by the VM, being carved out. Add ioctl command logic to get the offset in enclave memory where to place the enclave image. Then the user space tooling copies the enclave image in the memory using the given memory offset. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * No changes. v7 -> v8 * Add custom error code for incorrect enclave image load info flag. v6 -> v7 * No changes. v5 -> v6 * Check for invalid enclave image load flags. v4 -> v5 * Check for the enclave not being started when invoking this ioctl call. * Remove log on copy_from_user() / copy_to_user() failure. v3 -> v4 * Use dev_err instead of custom NE log pattern. * Set enclave image load offset based on flags. * Update the naming for the ioctl command from metadata to info. v2 -> v3 * No changes. v1 -> v2 * New in v2. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-11-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add logic for setting an enclave vCPUAndra Paraschiv
An enclave, before being started, has its resources set. One of its resources is CPU. A NE CPU pool is set and enclave CPUs are chosen from it. Offline the CPUs from the NE CPU pool during the pool setup and online them back during the NE CPU pool teardown. The CPU offline is necessary so that there would not be more vCPUs than physical CPUs available to the primary / parent VM. In that case the CPUs would be overcommitted and would change the initial configuration of the primary / parent VM of having dedicated vCPUs to physical CPUs. The enclave CPUs need to be full cores and from the same NUMA node. CPU 0 and its siblings have to remain available to the primary / parent VM. Add ioctl command logic for setting an enclave vCPU. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Use the ne_devs data structure to get the refs for the NE PCI device. v7 -> v8 * No changes. v6 -> v7 * Check for error return value when setting the kernel parameter string. * Use the NE misc device parent field to get the NE PCI device. * Update the naming and add more comments to make more clear the logic of handling full CPU cores and dedicating them to the enclave. * Calculate the number of threads per core and not use smp_num_siblings that is x86 specific. v5 -> v6 * Check CPUs are from the same NUMA node before going through CPU siblings during the NE CPU pool setup. * Update documentation to kernel-doc format. v4 -> v5 * Set empty string in case of invalid NE CPU pool. * Clear NE CPU pool mask on pool setup failure. * Setup NE CPU cores out of the NE CPU pool. * Early exit on NE CPU pool setup if enclave(s) already running. * Remove sanity checks for situations that shouldn't happen, only if buggy system or broken logic at all. * Add check for maximum vCPU id possible before looking into the CPU pool. * Remove log on copy_from_user() / copy_to_user() failure and on admin capability check for setting the NE CPU pool. * Update the ioctl call to not create a file descriptor for the vCPU. * Split the CPU pool usage logic in 2 separate functions - one to get a CPU from the pool and the other to check the given CPU is available in the pool. v3 -> v4 * Setup the NE CPU pool at runtime via a sysfs file for the kernel parameter. * Check enclave CPUs to be from the same NUMA node. * Use dev_err instead of custom NE log pattern. * Update the NE ioctl call to match the decoupling from the KVM API. v2 -> v3 * Remove the WARN_ON calls. * Update static calls sanity checks. * Update kzfree() calls to kfree(). * Remove file ops that do nothing for now - open, ioctl and release. v1 -> v2 * Add log pattern for NE. * Update goto labels to match their purpose. * Remove the BUG_ON calls. * Check if enclave state is init when setting enclave vCPU. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Alexandru Vasile <lexnv@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-10-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Add logic for creating an enclave VMAndra Paraschiv
Add ioctl command logic for enclave VM creation. It triggers a slot allocation. The enclave resources will be associated with this slot and it will be used as an identifier for triggering enclave run. Return a file descriptor, namely enclave fd. This is further used by the associated user space enclave process to set enclave resources and trigger enclave termination. The poll function is implemented in order to notify the enclave process when an enclave exits without a specific enclave termination command trigger e.g. when an enclave crashes. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Use the ne_devs data structure to get the refs for the NE PCI device. v7 -> v8 * No changes. v6 -> v7 * Use the NE misc device parent field to get the NE PCI device. * Update the naming and add more comments to make more clear the logic of handling full CPU cores and dedicating them to the enclave. v5 -> v6 * Update the code base to init the ioctl function in this patch. * Update documentation to kernel-doc format. v4 -> v5 * Release the reference to the NE PCI device on create VM error. * Close enclave fd on copy_to_user() failure; rename fd to enclave fd while at it. * Remove sanity checks for situations that shouldn't happen, only if buggy system or broken logic at all. * Remove log on copy_to_user() failure. v3 -> v4 * Use dev_err instead of custom NE log pattern. * Update the NE ioctl call to match the decoupling from the KVM API. * Add metadata for the NUMA node for the enclave memory and CPUs. v2 -> v3 * Remove the WARN_ON calls. * Update static calls sanity checks. * Update kzfree() calls to kfree(). * Remove file ops that do nothing for now - open. v1 -> v2 * Add log pattern for NE. * Update goto labels to match their purpose. * Remove the BUG_ON calls. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Alexandru Vasile <lexnv@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-9-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Init misc device providing the ioctl interfaceAndra Paraschiv
The Nitro Enclaves driver provides an ioctl interface to the user space for enclave lifetime management e.g. enclave creation / termination and setting enclave resources such as memory and CPU. This ioctl interface is mapped to a Nitro Enclaves misc device. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Use the ne_devs data structure to get the refs for the NE misc device in the NE PCI device driver logic. v7 -> v8 * Add define for the CID of the primary / parent VM. * Update the NE PCI driver shutdown logic to include misc device deregister. v6 -> v7 * Set the NE PCI device the parent of the NE misc device to be able to use it in the ioctl logic. * Update the naming and add more comments to make more clear the logic of handling full CPU cores and dedicating them to the enclave. v5 -> v6 * Remove the ioctl to query API version. * Update documentation to kernel-doc format. v4 -> v5 * Update the size of the NE CPU pool string from 4096 to 512 chars. v3 -> v4 * Use dev_err instead of custom NE log pattern. * Remove the NE CPU pool init during kernel module loading, as the CPU pool is now setup at runtime, via a sysfs file for the kernel parameter. * Add minimum enclave memory size definition. v2 -> v3 * Remove the GPL additional wording as SPDX-License-Identifier is already in place. * Remove the WARN_ON calls. * Remove linux/bug and linux/kvm_host includes that are not needed. * Remove "ratelimited" from the logs that are not in the ioctl call paths. * Remove file ops that do nothing for now - open and release. v1 -> v2 * Add log pattern for NE. * Update goto labels to match their purpose. * Update ne_cpu_pool data structure to include the global mutex. * Update NE misc device mode to 0660. * Check if the CPU siblings are included in the NE CPU pool, as full CPU cores are given for the enclave(s). Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-8-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-09-22nitro_enclaves: Handle out-of-band PCI device eventsAndra Paraschiv
In addition to the replies sent by the Nitro Enclaves PCI device in response to command requests, out-of-band enclave events can happen e.g. an enclave crashes. In this case, the Nitro Enclaves driver needs to be aware of the event and notify the corresponding user space process that abstracts the enclave. Register an MSI-X interrupt vector to be used for this kind of out-of-band events. The interrupt notifies that the state of an enclave changed and the driver logic scans the state of each running enclave to identify for which this notification is intended. Create an workqueue to handle the out-of-band events. Notify user space enclave process that is using a polling mechanism on the enclave fd. Changelog v9 -> v10 * Update commit message to include the changelog before the SoB tag(s). v8 -> v9 * Use the reference to the pdev directly from the ne_pci_dev instead of the one from the enclave data structure. v7 -> v8 * No changes. v6 -> v7 * No changes. v5 -> v6 * Update documentation to kernel-doc format. v4 -> v5 * Remove sanity checks for situations that shouldn't happen, only if buggy system or broken logic at all. v3 -> v4 * Use dev_err instead of custom NE log pattern. * Return IRQ_NONE when interrupts are not handled. v2 -> v3 * Remove the WARN_ON calls. * Update static calls sanity checks. * Remove "ratelimited" from the logs that are not in the ioctl call paths. v1 -> v2 * Add log pattern for NE. * Update goto labels to match their purpose. Reviewed-by: Alexander Graf <graf@amazon.com> Signed-off-by: Alexandru-Catalin Vasile <lexnv@amazon.com> Signed-off-by: Andra Paraschiv <andraprs@amazon.com> Link: https://lore.kernel.org/r/20200921121732.44291-7-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
generated by cgit v1.2.3 (git 2.39.1) at 2025-07-31 12:46:50 +0000