linux-stable.git/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c, branch v6.2 Linux kernel stable tree drm/amdkfd: Fix NULL pointer error for GC 11.0.1 on mGPU 2023-01-10T23:11:08+00:00 Eric Huang jinhuieric.huang@amd.com 2023-01-05T19:01:18+00:00 a6941f89d7c6a6ba49316bbd7da2fb2f719119a7 The point bo->kfd_bo is NULL for queue's write pointer BO when creating queue on mGPU. To avoid using the pointer fixes the error. Signed-off-by: Eric Huang <jinhuieric.huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The point bo->kfd_bo is NULL for queue's write pointer BO
when creating queue on mGPU. To avoid using the pointer
fixes the error.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Fix double release compute pasid 2022-12-20T17:58:06+00:00 Philip Yang Philip.Yang@amd.com 2022-12-13T05:50:03+00:00 1a799c4c190ea9f0e81028e3eb3037ed0ab17ff5 If kfd_process_device_init_vm returns failure after vm is converted to compute vm and vm->pasid set to compute pasid, KFD will not take pdd->drm_file reference. As a result, drm close file handler maybe called to release the compute pasid before KFD process destroy worker to release the same pasid and set vm->pasid to zero, this generates below WARNING backtrace and NULL pointer access. Add helper amdgpu_amdkfd_gpuvm_set_vm_pasid and call it at the last step of kfd_process_device_init_vm, to ensure vm pasid is the original pasid if acquiring vm failed or is the compute pasid with pdd->drm_file reference taken to avoid double release same pasid. amdgpu: Failed to create process VM object ida_free called for id=32770 which is not allocated. WARNING: CPU: 57 PID: 72542 at ../lib/idr.c:522 ida_free+0x96/0x140 RIP: 0010:ida_free+0x96/0x140 Call Trace: amdgpu_pasid_free_delayed+0xe1/0x2a0 [amdgpu] amdgpu_driver_postclose_kms+0x2d8/0x340 [amdgpu] drm_file_free.part.13+0x216/0x270 [drm] drm_close_helper.isra.14+0x60/0x70 [drm] drm_release+0x6e/0xf0 [drm] __fput+0xcc/0x280 ____fput+0xe/0x20 task_work_run+0x96/0xc0 do_exit+0x3d0/0xc10 BUG: kernel NULL pointer dereference, address: 0000000000000000 RIP: 0010:ida_free+0x76/0x140 Call Trace: amdgpu_pasid_free_delayed+0xe1/0x2a0 [amdgpu] amdgpu_driver_postclose_kms+0x2d8/0x340 [amdgpu] drm_file_free.part.13+0x216/0x270 [drm] drm_close_helper.isra.14+0x60/0x70 [drm] drm_release+0x6e/0xf0 [drm] __fput+0xcc/0x280 ____fput+0xe/0x20 task_work_run+0x96/0xc0 do_exit+0x3d0/0xc10 Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
If kfd_process_device_init_vm returns failure after vm is converted to
compute vm and vm->pasid set to compute pasid, KFD will not take
pdd->drm_file reference. As a result, drm close file handler maybe
called to release the compute pasid before KFD process destroy worker to
release the same pasid and set vm->pasid to zero, this generates below
WARNING backtrace and NULL pointer access.

Add helper amdgpu_amdkfd_gpuvm_set_vm_pasid and call it at the last step
of kfd_process_device_init_vm, to ensure vm pasid is the original pasid
if acquiring vm failed or is the compute pasid with pdd->drm_file
reference taken to avoid double release same pasid.

 amdgpu: Failed to create process VM object
 ida_free called for id=32770 which is not allocated.
 WARNING: CPU: 57 PID: 72542 at ../lib/idr.c:522 ida_free+0x96/0x140
 RIP: 0010:ida_free+0x96/0x140
 Call Trace:
  amdgpu_pasid_free_delayed+0xe1/0x2a0 [amdgpu]
  amdgpu_driver_postclose_kms+0x2d8/0x340 [amdgpu]
  drm_file_free.part.13+0x216/0x270 [drm]
  drm_close_helper.isra.14+0x60/0x70 [drm]
  drm_release+0x6e/0xf0 [drm]
  __fput+0xcc/0x280
  ____fput+0xe/0x20
  task_work_run+0x96/0xc0
  do_exit+0x3d0/0xc10

 BUG: kernel NULL pointer dereference, address: 0000000000000000
 RIP: 0010:ida_free+0x76/0x140
 Call Trace:
  amdgpu_pasid_free_delayed+0xe1/0x2a0 [amdgpu]
  amdgpu_driver_postclose_kms+0x2d8/0x340 [amdgpu]
  drm_file_free.part.13+0x216/0x270 [drm]
  drm_close_helper.isra.14+0x60/0x70 [drm]
  drm_release+0x6e/0xf0 [drm]
  __fput+0xcc/0x280
  ____fput+0xe/0x20
  task_work_run+0x96/0xc0
  do_exit+0x3d0/0xc10

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Add notifier lock for KFD userptrs 2022-12-14T14:48:05+00:00 Felix Kuehling Felix.Kuehling@amd.com 2021-04-22T01:09:54+00:00 f95f51a4c3357eabf74fe14ab7daa5b5c0422b27 Add a per-process MMU notifier lock for processing notifiers from userptrs. Use that lock to properly synchronize page table updates with MMU notifiers. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Xiaogang Chen<Xiaogang.Chen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Add a per-process MMU notifier lock for processing notifiers from
userptrs. Use that lock to properly synchronize page table updates with
MMU notifiers.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Xiaogang Chen<Xiaogang.Chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Fix memory leakage 2022-11-29T16:03:39+00:00 Konstantin Meskhidze konstantin.meskhidze@huawei.com 2022-11-29T04:02:54+00:00 75818afff631e1ea785a82c3e8bb82eb0dee539c This patch fixes potential memory leakage and seg fault in _gpuvm_import_dmabuf() function Fixes: d4ec4bdc0bd5 ("drm/amdkfd: Allow access for mmapping KFD BOs") Signed-off-by: Konstantin Meskhidze <konstantin.meskhidze@huawei.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
This patch fixes potential memory leakage and seg fault
in  _gpuvm_import_dmabuf() function

Fixes: d4ec4bdc0bd5 ("drm/amdkfd: Allow access for mmapping KFD BOs")
Signed-off-by: Konstantin Meskhidze <konstantin.meskhidze@huawei.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: rename the files for HMM handling 2022-11-17T05:23:36+00:00 Christian König christian.koenig@amd.com 2022-11-09T11:28:46+00:00 d9483ecd327b7537c6a51cab515b5faad21b8200 Clean that up a bit, no functional change. Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
Clean that up a bit, no functional change.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: fix userptr HMM range handling v2 2022-11-17T05:23:30+00:00 Christian König christian.koenig@amd.com 2022-11-10T11:31:41+00:00 fec8fdb54e8f74d88951c9f998f47bf4f2031fe0 The basic problem here is that it's not allowed to page fault while holding the reservation lock. So it can happen that multiple processes try to validate an userptr at the same time. Work around that by putting the HMM range object into the mutex protected bo list for now. v2: make sure range is set to NULL in case of an error Signed-off-by: Christian König <christian.koenig@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> CC: stable@vger.kernel.org Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The basic problem here is that it's not allowed to page fault while
holding the reservation lock.

So it can happen that multiple processes try to validate an userptr
at the same time.

Work around that by putting the HMM range object into the mutex
protected bo list for now.

v2: make sure range is set to NULL in case of an error

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Fix a memory limit issue 2022-11-15T18:35:16+00:00 Eric Huang jinhuieric.huang@amd.com 2022-11-14T16:43:48+00:00 48fb1ecf9371b649202c85ba6d44f5204e88bfc8 It is to resolve a regression, which fails to allocate VRAM due to no free memory in application, the reason is we add check of vram_pin_size for memory limit, and application is pinning the memory for Peerdirect, KFD should not count it in memory limit. So removing vram_pin_size will resolve it. Signed-off-by: Eric Huang <jinhuieric.huang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
It is to resolve a regression, which fails to allocate
VRAM due to no free memory in application, the reason
is we add check of vram_pin_size for memory limit, and
application is pinning the memory for Peerdirect, KFD
should not count it in memory limit. So removing
vram_pin_size will resolve it.

Signed-off-by: Eric Huang <jinhuieric.huang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Set MTYPE in PTE based on BO flags 2022-11-09T22:41:42+00:00 Felix Kuehling Felix.Kuehling@amd.com 2022-08-26T22:22:35+00:00 d1a372af1c3d834c2346b2e822cd6c40abc09866 The same BO may need different MTYPEs and SNOOP flags in PTEs depending on its current location relative to the mapping GPU. Setting MTYPEs from clients ahead of time is not practical for coherent memory sharing. Instead determine the correct MTYPE for the desired coherence model and current BO location when updating the page tables. To maintain backwards compatibility with MTYPE-selection in AMDGPU_VA_OP_MAP, the coherence-model-based MTYPE selection is only applied if it chooses an MTYPE other than MTYPE_NC (the default). Add two AMDGPU_GEM_CREATE_... flags to indicate the coherence model. The default if no flag is specified is non-coherent (i.e. coarse-grained coherent at dispatch boundaries). Update amdgpu_amdkfd_gpuvm.c to use this new method to choose the correct MTYPE depending on the current memory location. v2: * check that bo is not NULL (e.g. PRT mappings) * Fix missing ~ bitmask in gmc_v11_0.c v3: * squash in "drm/amdgpu: Inherit coherence flags on dmabuf import" Suggested-by: Christian König <christian.koenig@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
The same BO may need different MTYPEs and SNOOP flags in PTEs depending
on its current location relative to the mapping GPU. Setting MTYPEs from
clients ahead of time is not practical for coherent memory sharing.
Instead determine the correct MTYPE for the desired coherence model and
current BO location when updating the page tables.

To maintain backwards compatibility with MTYPE-selection in
AMDGPU_VA_OP_MAP, the coherence-model-based MTYPE selection is only
applied if it chooses an MTYPE other than MTYPE_NC (the default).

Add two AMDGPU_GEM_CREATE_... flags to indicate the coherence model. The
default if no flag is specified is non-coherent (i.e. coarse-grained
coherent at dispatch boundaries).

Update amdgpu_amdkfd_gpuvm.c to use this new method to choose the
correct MTYPE depending on the current memory location.

v2:
* check that bo is not NULL (e.g. PRT mappings)
* Fix missing ~ bitmask in gmc_v11_0.c
v3:
* squash in "drm/amdgpu: Inherit coherence flags on dmabuf import"

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Remove skiping userptr buffer mapping when mmu notifier marks it as invalid 2022-11-04T20:05:54+00:00 Xiaogang Chen xiaogang.chen@amd.com 2022-10-29T00:13:31+00:00 fcf00f8d29f2fc6bf00531a1447be28b99073cc3 mmu notifier does not always hold mm->sem during call back. That causes a race condition between kfd userprt buffer mapping and mmu notifier which leds to gpu shadder or SDMA access userptr buffer before it has been mapped to gpu VM. Always map userptr buffer to avoid that though it may make some userprt buffers mapped two times. Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
mmu notifier does not always hold mm->sem during call back. That causes
a race condition between kfd userprt buffer mapping and mmu notifier
which leds to gpu shadder or SDMA access userptr buffer before it has been
mapped to gpu VM. Always map userptr buffer to avoid that though it may make
some userprt buffers mapped two times.

Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdkfd: Fix memory leak in kfd_mem_dmamap_userptr() 2022-10-24T18:34:27+00:00 Rafael Mendonca rafaelmendsr@gmail.com 2022-10-18T01:27:50+00:00 7b5a4d7b9e2952a15c8d2b2391dfacd7ce841a1a If the number of pages from the userptr BO differs from the SG BO then the allocated memory for the SG table doesn't get freed before returning -EINVAL, which may lead to a memory leak in some error paths. Fix this by checking the number of pages before allocating memory for the SG table. Fixes: 264fb4d332f5 ("drm/amdgpu: Add multi-GPU DMA mapping helpers") Signed-off-by: Rafael Mendonca <rafaelmendsr@gmail.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> 
If the number of pages from the userptr BO differs from the SG BO then the
allocated memory for the SG table doesn't get freed before returning
-EINVAL, which may lead to a memory leak in some error paths. Fix this by
checking the number of pages before allocating memory for the SG table.

Fixes: 264fb4d332f5 ("drm/amdgpu: Add multi-GPU DMA mapping helpers")
Signed-off-by: Rafael Mendonca <rafaelmendsr@gmail.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>