user/sven/linux.git/drivers/gpu/drm/amd/amdkfd, branch v5.10.67

drm/amdkfd: Account for SH/SE count when setting up cu masks.

2021-09-18T11:40:33Z

[ Upstream commit 1ec06c2dee679e9f089e78ed20cb74ee90155f61 ] On systems with multiple SH per SE compute_static_thread_mgmt_se# is split into independent masks, one for each SH, in the upper and lower 16 bits. We need to detect this and apply cu masking to each SH. The cu mask bits are assigned first to each SE, then to alternate SHs, then finally to higher CU id. This ensures that the maximum number of SPIs are engaged as early as possible while balancing CU assignment to each SH. v2: Use max SH/SE rather than max SH in cu_per_sh. v3: Fix comment blocks, ensure se_mask is initially zero filled, and correctly assign se.sh.cu positions to unset bits in cu_mask. Signed-off-by: Sean Keely Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: fix sysfs kobj leak

2021-07-20T14:05:49Z

[ Upstream commit dcdb4d904b4bd3078fe8d4d24b1658560d6078ef ] 3 cases of kobj leak, which causes memory leak: kobj_type must have release() method to free memory from release callback. Don't need NULL default_attrs to init kobj. sysfs files created under kobj_status should be removed with kobj_status as parent kobject. Remove queue sysfs files when releasing queue from process MMU notifier release callback. Signed-off-by: Philip Yang Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Walk through list with dqm lock hold

2021-07-19T07:44:51Z

[ Upstream commit 56f221b6389e7ab99c30bbf01c71998ae92fc584 ] To avoid any list corruption. Signed-off-by: xinhui pan Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Fix circular lock in nocpsch path

2021-07-19T07:44:50Z

[ Upstream commit a7b2451d31cfa2e8aeccf3b35612ce33f02371fc ] Calling free_mqd inside of destroy_queue_nocpsch_locked can cause a circular lock. destroy_queue_nocpsch_locked is called under a DQM lock, which is taken in MMU notifiers, potentially in FS reclaim context. Taking another lock, which is BO reservation lock from free_mqd, while causing an FS reclaim inside the DQM lock creates a problematic circular lock dependency. Therefore move free_mqd out of destroy_queue_nocpsch_locked and call it after unlocking DQM. Signed-off-by: Amber Lin Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: fix circular locking on get_wave_state

2021-07-19T07:44:50Z

[ Upstream commit 63f6e01237257e7226efc5087f3f0b525d320f54 ] get_wave_state acquires the mmap_lock on copy_to_user but so do mmu_notifiers. mmu_notifiers allows dqm locking so do get_wave_state outside the dqm_lock to prevent circular locking. v2: squash in unused variable removal. Signed-off-by: Jonathan Kim Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: fix build error with AMD_IOMMU_V2=m

2021-05-14T07:50:24Z

[ Upstream commit 1e87068570a2cc4db5f95a881686add71729e769 ] Using 'imply AMD_IOMMU_V2' does not guarantee that the driver can link against the exported functions. If the GPU driver is built-in but the IOMMU driver is a loadable module, the kfd_iommu.c file is indeed built but does not work: x86_64-linux-ld: drivers/gpu/drm/amd/amdkfd/kfd_iommu.o: in function `kfd_iommu_bind_process_to_device': kfd_iommu.c:(.text+0x516): undefined reference to `amd_iommu_bind_pasid' x86_64-linux-ld: drivers/gpu/drm/amd/amdkfd/kfd_iommu.o: in function `kfd_iommu_unbind_process': kfd_iommu.c:(.text+0x691): undefined reference to `amd_iommu_unbind_pasid' x86_64-linux-ld: drivers/gpu/drm/amd/amdkfd/kfd_iommu.o: in function `kfd_iommu_suspend': kfd_iommu.c:(.text+0x966): undefined reference to `amd_iommu_set_invalidate_ctx_cb' x86_64-linux-ld: kfd_iommu.c:(.text+0x97f): undefined reference to `amd_iommu_set_invalid_ppr_cb' x86_64-linux-ld: kfd_iommu.c:(.text+0x9a4): undefined reference to `amd_iommu_free_device' x86_64-linux-ld: drivers/gpu/drm/amd/amdkfd/kfd_iommu.o: in function `kfd_iommu_resume': kfd_iommu.c:(.text+0xa9a): undefined reference to `amd_iommu_init_device' x86_64-linux-ld: kfd_iommu.c:(.text+0xadc): undefined reference to `amd_iommu_set_invalidate_ctx_cb' x86_64-linux-ld: kfd_iommu.c:(.text+0xaff): undefined reference to `amd_iommu_set_invalid_ppr_cb' x86_64-linux-ld: kfd_iommu.c:(.text+0xc72): undefined reference to `amd_iommu_bind_pasid' x86_64-linux-ld: kfd_iommu.c:(.text+0xe08): undefined reference to `amd_iommu_set_invalidate_ctx_cb' x86_64-linux-ld: kfd_iommu.c:(.text+0xe26): undefined reference to `amd_iommu_set_invalid_ppr_cb' x86_64-linux-ld: kfd_iommu.c:(.text+0xe42): undefined reference to `amd_iommu_free_device' Use IS_REACHABLE to only build IOMMU-V2 support if the amd_iommu symbols are reachable by the amdkfd driver. Output a warning if they are not, because that may not be what the user was expecting. Fixes: 64d1c3a43a6f ("drm/amdkfd: Centralize IOMMUv2 code and make it conditional") Reported-by: Arnd Bergmann Signed-off-by: Felix Kuehling Reviewed-by: Christian König Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Fix cat debugfs hang_hws file causes system crash bug

2021-05-11T12:47:30Z

[ Upstream commit d73610211eec8aa027850982b1a48980aa1bc96e ] Here is the system crash log: [ 1272.884438] BUG: unable to handle kernel NULL pointer dereference at (null) [ 1272.884444] IP: [< (null)>] (null) [ 1272.884447] PGD 825b09067 PUD 8267c8067 PMD 0 [ 1272.884452] Oops: 0010 [#1] SMP [ 1272.884509] CPU: 13 PID: 3485 Comm: cat Kdump: loaded Tainted: G [ 1272.884515] task: ffff9a38dbd4d140 ti: ffff9a37cd3b8000 task.ti: ffff9a37cd3b8000 [ 1272.884517] RIP: 0010:[<0000000000000000>] [< (null)>] (null) [ 1272.884520] RSP: 0018:ffff9a37cd3bbe68 EFLAGS: 00010203 [ 1272.884522] RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000014d5f [ 1272.884524] RDX: fffffffffffffff4 RSI: 0000000000000001 RDI: ffff9a38aca4d200 [ 1272.884526] RBP: ffff9a37cd3bbed0 R08: ffff9a38dcd5f1a0 R09: ffff9a31ffc07300 [ 1272.884527] R10: ffff9a31ffc07300 R11: ffffffffaddd5e9d R12: ffff9a38b4e0fb00 [ 1272.884529] R13: 0000000000000001 R14: ffff9a37cd3bbf18 R15: ffff9a38aca4d200 [ 1272.884532] FS: 00007feccaa67740(0000) GS:ffff9a38dcd40000(0000) knlGS:0000000000000000 [ 1272.884534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1272.884536] CR2: 0000000000000000 CR3: 00000008267c0000 CR4: 00000000003407e0 [ 1272.884537] Call Trace: [ 1272.884544] [] ? seq_read+0x130/0x440 [ 1272.884548] [] vfs_read+0x9f/0x170 [ 1272.884552] [] SyS_read+0x7f/0xf0 [ 1272.884557] [] system_call_fastpath+0x22/0x27 [ 1272.884558] Code: Bad RIP value. [ 1272.884562] RIP [< (null)>] (null) [ 1272.884564] RSP [ 1272.884566] CR2: 0000000000000000 Signed-off-by: Qu Huang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Fix UBSAN shift-out-of-bounds warning

2021-05-11T12:47:25Z

[ Upstream commit 50e2fc36e72d4ad672032ebf646cecb48656efe0 ] If get_num_sdma_queues or get_num_xgmi_sdma_queues is 0, we end up doing a shift operation where the number of bits shifted equals number of bits in the operand. This behaviour is undefined. Set num_sdma_queues or num_xgmi_sdma_queues to ULLONG_MAX, if the count is >= number of bits in the operand. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1472 Reported-by: Lyude Paul Signed-off-by: Anson Jacob Reviewed-by: Alex Deucher Reviewed-by: Felix Kuehling Tested-by: Lyude Paul Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: dqm fence memory corruption

2021-04-07T13:00:10Z

commit e92049ae4548ba09e53eaa9c8f6964b07ea274c9 upstream. Amdgpu driver uses 4-byte data type as DQM fence memory, and transmits GPU address of fence memory to microcode through query status PM4 message. However, query status PM4 message definition and microcode processing are all processed according to 8 bytes. Fence memory only allocates 4 bytes of memory, but microcode does write 8 bytes of memory, so there is a memory corruption. Changes since v1: * Change dqm->fence_addr as a u64 pointer to fix this issue, also fix up query_status and amdkfd_fence_wait_timeout function uses 64 bit fence value to make them consistent. Signed-off-by: Qu Huang Reviewed-by: Felix Kuehling Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman

drm/amdkfd: Fix recursive lock warnings

2021-03-04T10:38:27Z

commit 1fb8b1fc4dd1035a264c81d15d41f05884cc8058 upstream. memalloc_nofs_save/restore are no longer sufficient to prevent recursive lock warnings when holding locks that can be taken in MMU notifiers. Use memalloc_noreclaim_save/restore instead. Fixes: f920e413ff9c ("mm: track mmu notifiers in fs_reclaim_acquire/release") CC: Daniel Vetter Reviewed-by: Philip Yang Signed-off-by: Felix Kuehling Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org # 5.10.x Signed-off-by: Greg Kroah-Hartman