- 06 11月, 2018 1 次提交
-
-
由 Amber Lin 提交于
After amdkfd module is merged into amdgpu, KFD can call amdgpu directly and no longer needs to use the function pointer. Replace those function pointers with functions if they are not ASIC dependent. Signed-off-by: NAmber Lin <Amber.Lin@amd.com> Acked-by: NChristian König <christian.koenig@amd.com> Reviewed-by: NAlex Deucher <alexander.deucher@amd.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 27 9月, 2018 1 次提交
-
-
由 Jay Cornwall 提交于
Wavefront context save data is of interest to userspace clients for debugging static wavefront state. The MQD contains two parameters required to parse the control stack and the control stack itself is kept in the MQD from gfx9 onwards. Add an ioctl to fetch the context save area and control stack offsets and to copy the control stack to a userspace address if it is kept in the MQD. Signed-off-by: NJay Cornwall <Jay.Cornwall@amd.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NAlex Deucher <alexander.deucher@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 11 9月, 2018 1 次提交
-
-
由 shaoyunl 提交于
v2: compile fix Signed-off-by: Nshaoyunl <Shaoyun.Liu@amd.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
-
- 15 7月, 2018 1 次提交
-
-
由 Felix Kuehling 提交于
CU-masking allows a KFD client to control the set of CUs used by a user mode queue for executing compute dispatches. This can be used for optimizing the partitioning of the GPU and minimize conflicts between concurrent tasks. Signed-off-by: NFlora Cui <flora.cui@amd.com> Signed-off-by: NKent Russell <kent.russell@amd.com> Signed-off-by: NEric Huang <JinHuiEric.Huang@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 12 7月, 2018 1 次提交
-
-
由 Shaoyun Liu 提交于
Lock KFD and evict existing queues on reset. Notify user mode by signaling hw_exception events. Signed-off-by: NShaoyun Liu <Shaoyun.Liu@amd.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 11 7月, 2018 1 次提交
-
-
由 Arnd Bergmann 提交于
getrawmonotonic64() and get_monotonic_boottime64() are deprecated because of the nonstandard naming. The replacement functions ktime_get_raw_ns() and ktime_get_boot_ns() also simplify the callers. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>. Signed-off-by: NArnd Bergmann <arnd@arndb.de> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 24 4月, 2018 3 次提交
-
-
由 Andres Rodriguez 提交于
Currently if a user requests clock counters for a node without a GPU resource we will always return EINVAL. Instead if no GPU resource is attached, fill the gpu_clock_counter argument with zeroes so that we may proceed and return valid CPU counters. Signed-off-by: NAndres Rodriguez <andres.rodriguez@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Wei Yongjun 提交于
Passing NULL pointer to PTR_ERR will result in return value of 0 indicating success which is clearly not what it is intended here. This patch returns -EINVAL instead. v2: change ret code to -ENODEV Fixes: 5ec7e028 ("drm/amdkfd: Add ioctls for GPUVM memory management") Signed-off-by: NWei Yongjun <weiyongjun1@huawei.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 kbuild test robot 提交于
Fixes: 5ec7e028 ("drm/amdkfd: Add ioctls for GPUVM memory management") Signed-off-by: NFengguang Wu <fengguang.wu@intel.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 02 5月, 2018 1 次提交
-
-
由 Philip Yang 提交于
Signed-off-by: NPhilip Yang <Philip.Yang@amd.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 24 4月, 2018 1 次提交
-
-
由 Dan Carpenter 提交于
args->n_devices is a u32 that comes from the user. The multiplication could overflow on 32 bit systems possibly leading to privilege escalation. Fixes: 5ec7e028 ("drm/amdkfd: Add ioctls for GPUVM memory management") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com> Reviewed-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 11 4月, 2018 2 次提交
-
-
由 Felix Kuehling 提交于
Allocate doorbells according to the doorbell routing information on SOC15 ASICs (Vega10 and later). On older ASICs we continue to use the queue_id as the doorbell ID to maintain compatibility with the Thunk. Signed-off-by: NShaoyun Liu <Shaoyun.Liu@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Harish Kasiviswanathan 提交于
Use bit-rotate for better clarity and remove _MASK from the #defines as these represent mmap types. Centralize all the parsing of the mmap offset in kfd_mmap and add device parameter to doorbell and reserved_mem map functions. Encode gpu_id into upper bits of vm_pgoff. This frees up the lower bits for encoding the the doorbell ID on Vega10. Signed-off-by: NHarish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 16 3月, 2018 4 次提交
-
-
由 Felix Kuehling 提交于
Simulate large-BAR system by exporting only visible memory. This limits the amount of available VRAM to the size of the BAR, but enables CPU access to VRAM. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Felix Kuehling 提交于
The events page must be accessible in user mode by the GPU and CPU as well as in kernel mode by the CPU. On dGPUs user mode virtual addresses are managed by the Thunk's GPU memory allocation code. Therefore we can't allocate the memory in kernel mode like we do on APUs. But KFD still needs to map the memory for kernel access. To facilitate this, the Thunk provides the buffer handle of the events page to KFD when creating the first event. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Felix Kuehling 提交于
v2: * Fix error handling after kfd_bind_process_to_device in kfd_ioctl_map_memory_to_gpu v3: * Add ioctl to acquire VM from a DRM FD v4: * Return number of successful map/unmap operations in failure cases * Facilitate partial retry after failed map/unmap * Added comments with parameter descriptions to new APIs * Defined AMDKFD_IOC_FREE_MEMORY_OF_GPU write-only Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Felix Kuehling 提交于
Currently the number of GPUs is limited by aperture placement options available on GFX7 and GFX8 hardware. This limitation is not necessary. Scratch and LDS represent per-work-item and per-work-group storage respectively. Different work-items and work-groups use the same virtual address to access their own data. Work running on different GPUs is by definition in different work-groups (different dispatches, in fact). That means the same virtual addresses can be used for these apertures on different GPUs. Add a new AMDKFD_IOC_GET_PROCESS_APERTURES_NEW ioctl that removes the artificial limitation on the number of GPUs that can be supported. The new ioctl allows user mode to query the number of GPUs to allocate enough memory for all GPUs to be reported. This deprecates AMDKFD_IOC_GET_PROCESS_APERTURES. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NChristian König <christian.koenig@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 05 1月, 2018 1 次提交
-
-
由 Felix Kuehling 提交于
Some dGPUs don't support HWS. Allow them to use a per-device sched_policy that may be different from the global default. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 28 11月, 2017 1 次提交
-
-
由 Philip Yang 提交于
After debugger is registered, the pqm_destroy_queue fails because is_debug is true, the queue should not be removed from process_queue_list since the count is not reduced. Test application calls debugger unregister without register debugger, add null pointer check protection to avoid crash for this case Signed-off-by: NPhilip Yang <Philip.Yang@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 15 11月, 2017 2 次提交
-
-
由 Felix Kuehling 提交于
A second-level user mode trap handler can be installed. The CWSR trap handler jumps to the secondary trap handler conditionally for any conditions not handled by it. This can be used e.g. for debugging or catching math exceptions. When CWSR is disabled, the user mode trap handler is installed as first level trap handler. Signed-off-by: NShaoyun.liu <shaoyun.liu@amd.com> Signed-off-by: NJay Cornwall <Jay.Cornwall@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Felix Kuehling 提交于
This hardware feature allows the GPU to preempt shader execution in the middle of a compute wave, save the state and restore it later to resume execution. Memory for saving the state is allocated per queue in user mode and the address and size passed to the create_queue ioctl. The size depends on the number of waves that can be in flight simultaneously on a given ASIC. Signed-off-by: NShaoyun.liu <shaoyun.liu@amd.com> Signed-off-by: NYong Zhao <yong.zhao@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 02 11月, 2017 1 次提交
-
-
由 Yair Shachar 提交于
Take the dbgmgr lock and unregister before destroying the debug manager. Do this before destroying the queues. v2: Correct locking order in kfd_ioctl_dbg_register to ake sure the process mutex and dbgmgr mutex are always taken in the same order. Signed-off-by: NYair Shachar <yair.shachar@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 28 10月, 2017 1 次提交
-
-
由 Felix Kuehling 提交于
Cleaned up the code while resolving some potential bugs and inconsistencies in the process. Clean-ups: * Remove enum kfd_event_wait_result, which duplicates KFD_IOC_EVENT_RESULT definitions * alloc_event_waiters can be called without holding p->event_mutex * Return an error code from copy_signaled_event_data instead of bool * Clean up error handling code paths to minimize duplication in kfd_wait_on_events Fixes: * Consistently return an error code from kfd_wait_on_events and set wait_result to KFD_IOC_WAIT_RESULT_FAIL in all failure cases. * Always call free_waiters while holding p->event_mutex * copy_signaled_event_data might sleep. Don't call it while the task state is TASK_INTERRUPTIBLE. Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Acked-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 27 9月, 2017 1 次提交
-
-
由 Yong Zhao 提交于
Signed-off-by: NYong Zhao <yong.zhao@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 08 9月, 2017 1 次提交
-
-
由 Colin Ian King 提交于
The call to kfd_device_by_id can potentially return null, so check that dev is null and return with -EINVAL to avoid a null pointer dereference. Detected by CoverityScan CID#1454629 ("Dereference null return value") Fixes: 5d71dbc3 ("drm/amdkfd: Implement image tiling mode support v2") Signed-off-by: NColin Ian King <colin.king@canonical.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 16 8月, 2017 6 次提交
-
-
由 Yong Zhao 提交于
v2: Removed hole in ioctl number space Signed-off-by: NYong Zhao <yong.zhao@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Moses Reuben 提交于
v2: * Renamed ALLOC_MEMORY_OF_SCRATCH to SET_SCRATCH_BACKING_VA * Removed size parameter from the ioctl, it was unused * Removed hole in ioctl number space * No more call to write_config_static_mem * Return correct error code from ioctl Signed-off-by: NMoses Reuben <moses.reuben@amd.com> Signed-off-by: NBen Goz <ben.goz@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Kent Russell 提交于
Remove gotos that do not feature any common cleanup, and use gotos instead of repeating cleanup commands. According to kernel.org: "The goto statement comes in handy when a function exits from multiple locations and some common work such as cleanup has to be done. If there is no cleanup needed then just return directly." v2: Applied review suggestions in create_queue_nocpsch Signed-off-by: NKent Russell <kent.russell@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Kent Russell 提交于
Upstream prefers the !x notation to x==NULL or x==false. Along those lines change the ==true or !=NULL references as well. Also make the references to !x the same, excluding () for readability. Signed-off-by: NKent Russell <kent.russell@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Kent Russell 提交于
Consolidate log commands so that dev_info(NULL, "Error...") uses the more accurate pr_err, remove the module name from the log (can be seen via dynamic debugging with +m), and the function name (can be seen via dynamic debugging with +f). We also don't need debug messages saying what function we're in. Those can be added by devs when needed Don't print vendor and device ID in error messages. They are typically the same for all GPUs in a multi-GPU system. So this doesn't add any value to the message. Lastly, remove parentheses around %d, %i and 0x%llX. According to kernel.org: "Printing numbers in parentheses (%d) adds no value and should be avoided." Signed-off-by: NKent Russell <kent.russell@amd.com> Signed-off-by: NYong Zhao <Yong.Zhao@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: NOded Gabbay <oded.gabbay@gmail.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Kent Russell 提交于
Using checkpatch.pl -f <file> showed a number of style issues. This patch addresses as many of them as possible. Some long lines have been left for readability, but attempts to minimize them have been made. v2: Broke long lines in gfx_v7 get_fw_version Signed-off-by: NKent Russell <kent.russell@amd.com> Signed-off-by: NFelix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 12 1月, 2017 1 次提交
-
-
由 Colin Ian King 提交于
Trivial fix to spelling mistake, rename kfd_ioctl_dbg_unrgesiter to kfd_ioctl_dbg_unregister Signed-off-by: NColin Ian King <colin.king@canonical.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 30 4月, 2016 2 次提交
-
-
由 Edward O'Callaghan 提交于
Found-By: Coccinelle Signed-off-by: NEdward O'Callaghan <eocallaghan@alterapraxis.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
由 Edward O'Callaghan 提交于
Found-By: Coccinelle Signed-off-by: NEdward O'Callaghan <eocallaghan@alterapraxis.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 23 3月, 2016 1 次提交
-
-
由 Andy Lutomirski 提交于
amdkfd wants to know syscall type, not task type. Check directly. Unfortunately, amdkfd is making nasty assumptions that a process' bitness is a well-defined constant thing. This isn't the case on x86. I don't know how much this matters, but this patch has no effect on generated code on x86, so amdkfd is equally broken with and without this patch. Signed-off-by: NAndy Lutomirski <luto@kernel.org> Cc: Oded Gabbay <oded.gabbay@gmail.com> Cc: David Airlie <airlied@linux.ie> Signed-off-by: NAndrew Morton <akpm@linux-foundation.org> Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
-
- 16 1月, 2016 1 次提交
-
-
由 Borislav Petkov 提交于
8f1d57c1 ("amdkfd: don't open-code memdup_user()") mistakenly uses an uninitialized local pointer, gcc complains: drivers/gpu/drm/amd/amdkfd/kfd_chardev.c: In function ‘kfd_ioctl_dbg_address_watch’: drivers/gpu/drm/amd/amdkfd/kfd_chardev.c:562:12: warning: ‘args_buff’ may be used uninitialized in this function [-Wmaybe-uninitialized] args_buff = memdup_user(args_buff, ^ Fix it. Signed-off-by: NBorislav Petkov <bp@suse.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
-
- 06 1月, 2016 1 次提交
-
-
由 Al Viro 提交于
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
-
- 30 8月, 2015 1 次提交
-
-
由 Christoph Hellwig 提交于
The latter is a default version of <asm/mman.h> and not for driver use. Signed-off-by: NChristoph Hellwig <hch@lst.de> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 16 6月, 2015 1 次提交
-
-
由 Dan Carpenter 提交于
buf_size_in_bytes must be large enough to hold ->num_watch_points and watch_mode so I have added a sizeof(int) * 2 to the minimum size. Also we have to subtract sizeof(*args) from the max args_idx limit so that it matches the allocation. Also I changed a > to >= for the last compare. Signed-off-by: NDan Carpenter <dan.carpenter@oracle.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-
- 03 6月, 2015 1 次提交
-
-
由 Yair Shachar 提交于
v2: - rename get_dbgmgr_mutex to kfd_get_dbgmgr_mutex to namespace it - change void* to uint64_t inside ioctl arguments - use kmalloc instead of kzalloc because we use copy_from_user immediately after it Signed-off-by: NYair Shachar <yair.shachar@amd.com> Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
-