summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdkfd
AgeCommit message (Collapse)AuthorFilesLines
2025-01-17drm/amdkfd: fixed page fault when enable MES shader debuggerJesse.zhang@amd.com1-0/+17
commit 9738609449c3e44d1afb73eecab4763362b57930 upstream. Initialize the process context address before setting the shader debugger. [ 260.781212] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:32 vmid:0 pasid:0) [ 260.781236] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x0000000000000000 from client 10 [ 260.781255] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00040A40 [ 260.781270] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: CPC (0x5) [ 260.781284] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x0 [ 260.781296] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x0 [ 260.781308] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x4 [ 260.781320] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x0 [ 260.781332] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 260.782017] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:32 vmid:0 pasid:0) [ 260.782039] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x0000000000000000 from client 10 [ 260.782058] amdgpu 0000:03:00.0: amdgpu: GCVM_L2_PROTECTION_FAULT_STATUS:0x00040A41 [ 260.782073] amdgpu 0000:03:00.0: amdgpu: Faulty UTCL2 client ID: CPC (0x5) [ 260.782087] amdgpu 0000:03:00.0: amdgpu: MORE_FAULTS: 0x1 [ 260.782098] amdgpu 0000:03:00.0: amdgpu: WALKER_ERROR: 0x0 [ 260.782110] amdgpu 0000:03:00.0: amdgpu: PERMISSION_FAULTS: 0x4 [ 260.782122] amdgpu 0000:03:00.0: amdgpu: MAPPING_ERROR: 0x0 [ 260.782137] amdgpu 0000:03:00.0: amdgpu: RW: 0x1 [ 260.782155] amdgpu 0000:03:00.0: amdgpu: [gfxhub] page fault (src_id:0 ring:32 vmid:0 pasid:0) [ 260.782166] amdgpu 0000:03:00.0: amdgpu: in page starting at address 0x0000000000000000 from client 10 Fixes: 438b39ac74e2 ("drm/amdkfd: pause autosuspend when creating pdd") Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3849 Signed-off-by: Jesse Zhang <jesse.zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> (cherry picked from commit 5b231f5bc9ff02ec5737f2ec95cdf15ac95088e9) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-01-09drm/amdkfd: Correct the migration DMA map directionPrike Liang1-2/+2
[ Upstream commit 5c3de6b02d38eb9386edf50490e050bb44398e40 ] The SVM DMA device map direction should be set the same as the DMA unmap setting, otherwise the DMA core will report the following warning. Before finialize this solution, there're some discussion on the DMA mapping type(stream-based or coherent) in this KFD migration case, followed by https://lore.kernel.org/all/04d4ab32 -45a1-4b88-86ee-fb0f35a0ca40@amd.com/T/. As there's no dma_sync_single_for_*() in the DMA buffer accessed that because this migration operation should be sync properly and automatically. Give that there's might not be a performance problem in various cache sync policy of DMA sync. Therefore, in order to simplify the DMA direction setting alignment, let's set the DMA map direction as BIDIRECTIONAL. [ 150.834218] WARNING: CPU: 8 PID: 1812 at kernel/dma/debug.c:1028 check_unmap+0x1cc/0x930 [ 150.834225] Modules linked in: amdgpu(OE) amdxcp drm_exec(OE) gpu_sched drm_buddy(OE) drm_ttm_helper(OE) ttm(OE) drm_suballoc_helper(OE) drm_display_helper(OE) drm_kms_helper(OE) i2c_algo_bit rpcsec_gss_krb5 auth_rpcgss nfsv4 nfs lockd grace netfs xt_conntrack xt_MASQUERADE nf_conntrack_netlink xfrm_user xfrm_algo iptable_nat xt_addrtype iptable_filter br_netfilter nvme_fabrics overlay nfnetlink_cttimeout nfnetlink openvswitch nsh nf_conncount nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 libcrc32c bridge stp llc sch_fq_codel intel_rapl_msr amd_atl intel_rapl_common snd_hda_codec_realtek snd_hda_codec_generic snd_hda_scodec_component snd_hda_codec_hdmi snd_hda_intel snd_intel_dspcfg edac_mce_amd snd_pci_acp6x snd_hda_codec snd_acp_config snd_hda_core snd_hwdep snd_soc_acpi kvm_amd sunrpc snd_pcm kvm binfmt_misc snd_seq_midi crct10dif_pclmul snd_seq_midi_event ghash_clmulni_intel sha512_ssse3 snd_rawmidi nls_iso8859_1 sha256_ssse3 sha1_ssse3 snd_seq aesni_intel snd_seq_device crypto_simd snd_timer cryptd input_leds [ 150.834310] wmi_bmof serio_raw k10temp rapl snd sp5100_tco ipmi_devintf soundcore ccp ipmi_msghandler cm32181 industrialio mac_hid msr parport_pc ppdev lp parport efi_pstore drm(OE) ip_tables x_tables pci_stub crc32_pclmul nvme ahci libahci i2c_piix4 r8169 nvme_core i2c_designware_pci realtek i2c_ccgx_ucsi video wmi hid_generic cdc_ether usbnet usbhid hid r8152 mii [ 150.834354] CPU: 8 PID: 1812 Comm: rocrtst64 Tainted: G OE 6.10.0-custom #492 [ 150.834358] Hardware name: AMD Majolica-RN/Majolica-RN, BIOS RMJ1009A 06/13/2021 [ 150.834360] RIP: 0010:check_unmap+0x1cc/0x930 [ 150.834363] Code: c0 4c 89 4d c8 e8 34 bf 86 00 4c 8b 4d c8 4c 8b 45 c0 48 8b 4d b8 48 89 c6 41 57 4c 89 ea 48 c7 c7 80 49 b4 84 e8 b4 81 f3 ff <0f> 0b 48 c7 c7 04 83 ac 84 e8 76 ba fc ff 41 8b 76 4c 49 8d 7e 50 [ 150.834365] RSP: 0018:ffffaac5023739e0 EFLAGS: 00010086 [ 150.834368] RAX: 0000000000000000 RBX: ffffffff8566a2e0 RCX: 0000000000000027 [ 150.834370] RDX: ffff8f6a8f621688 RSI: 0000000000000001 RDI: ffff8f6a8f621680 [ 150.834372] RBP: ffffaac502373a30 R08: 00000000000000c9 R09: ffffaac502373850 [ 150.834373] R10: ffffaac502373848 R11: ffffffff84f46328 R12: ffffaac502373a40 [ 150.834375] R13: ffff8f6741045330 R14: ffff8f6741a77700 R15: ffffffff84ac831b [ 150.834377] FS: 00007faf0fc94c00(0000) GS:ffff8f6a8f600000(0000) knlGS:0000000000000000 [ 150.834379] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 150.834381] CR2: 00007faf0b600020 CR3: 000000010a52e000 CR4: 0000000000350ef0 [ 150.834383] Call Trace: [ 150.834385] <TASK> [ 150.834387] ? show_regs+0x6d/0x80 [ 150.834393] ? __warn+0x8c/0x140 [ 150.834397] ? check_unmap+0x1cc/0x930 [ 150.834400] ? report_bug+0x193/0x1a0 [ 150.834406] ? handle_bug+0x46/0x80 [ 150.834410] ? exc_invalid_op+0x1d/0x80 [ 150.834413] ? asm_exc_invalid_op+0x1f/0x30 [ 150.834420] ? check_unmap+0x1cc/0x930 [ 150.834425] debug_dma_unmap_page+0x86/0x90 [ 150.834431] ? srso_return_thunk+0x5/0x5f [ 150.834435] ? rmap_walk+0x28/0x50 [ 150.834438] ? srso_return_thunk+0x5/0x5f [ 150.834441] ? remove_migration_ptes+0x79/0x80 [ 150.834445] ? srso_return_thunk+0x5/0x5f [ 150.834448] dma_unmap_page_attrs+0xfa/0x1d0 [ 150.834453] svm_range_dma_unmap_dev+0x8a/0xf0 [amdgpu] [ 150.834710] svm_migrate_ram_to_vram+0x361/0x740 [amdgpu] [ 150.834914] svm_migrate_to_vram+0xa8/0xe0 [amdgpu] [ 150.835111] svm_range_set_attr+0xff2/0x1450 [amdgpu] [ 150.835311] svm_ioctl+0x4a/0x50 [amdgpu] [ 150.835510] kfd_ioctl_svm+0x54/0x90 [amdgpu] [ 150.835701] kfd_ioctl+0x3c2/0x530 [amdgpu] [ 150.835888] ? __pfx_kfd_ioctl_svm+0x10/0x10 [amdgpu] [ 150.836075] ? srso_return_thunk+0x5/0x5f [ 150.836080] ? tomoyo_file_ioctl+0x20/0x30 [ 150.836086] __x64_sys_ioctl+0x9c/0xd0 [ 150.836091] x64_sys_call+0x1219/0x20d0 [ 150.836095] do_syscall_64+0x51/0x120 [ 150.836098] entry_SYSCALL_64_after_hwframe+0x76/0x7e [ 150.836102] RIP: 0033:0x7faf0f11a94f [ 150.836105] Code: 00 48 89 44 24 18 31 c0 48 8d 44 24 60 c7 04 24 10 00 00 00 48 89 44 24 08 48 8d 44 24 20 48 89 44 24 10 b8 10 00 00 00 0f 05 <41> 89 c0 3d 00 f0 ff ff 77 1f 48 8b 44 24 18 64 48 2b 04 25 28 00 [ 150.836107] RSP: 002b:00007ffeced26bc0 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 [ 150.836110] RAX: ffffffffffffffda RBX: 000055c683528fb0 RCX: 00007faf0f11a94f [ 150.836112] RDX: 00007ffeced26c60 RSI: 00000000c0484b20 RDI: 0000000000000003 [ 150.836114] RBP: 00007ffeced26c50 R08: 0000000000000000 R09: 0000000000000001 [ 150.836115] R10: 0000000000000032 R11: 0000000000000246 R12: 000055c683528bd0 [ 150.836117] R13: 0000000000000000 R14: 0000000000000021 R15: 0000000000000000 [ 150.836122] </TASK> [ 150.836124] ---[ end trace 0000000000000000 ]--- Signed-off-by: Prike Liang <Prike.Liang@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2025-01-02drm/amdkfd: pause autosuspend when creating pddJesse.zhang@amd.com2-21/+17
[ Upstream commit 438b39ac74e2a9dc0a5c9d653b7d8066877e86b1 ] When using MES creating a pdd will require talking to the GPU to setup the relevant context. The code here forgot to wake up the GPU in case it was in suspend, this causes KVM to EFAULT for passthrough GPU for example. This issue can be masked if the GPU was woken up by other things (e.g. opening the KMS node) first and have not yet gone to sleep. v4: do the allocation of proc_ctx_bo in a lazy fashion when the first queue is created in a process (Felix) Signed-off-by: Jesse Zhang <jesse.zhang@amd.com> Reviewed-by: Yunxiang Li <Yunxiang.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin <sashal@kernel.org>
2025-01-02drm/amdkfd: Use device based logging for errorsLijo Lazar5-45/+74
[ Upstream commit 62ec7d38b769ccf33b1080e69c2ae5b7344d116d ] Convert some pr_* to some dev_* APIs to identify the device. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Stable-dep-of: 438b39ac74e2 ("drm/amdkfd: pause autosuspend when creating pdd") Signed-off-by: Sasha Levin <sashal@kernel.org>
2025-01-02drm/amdkfd: drop struct kfd_cu_infoAlex Deucher3-57/+48
[ Upstream commit 0021d70a0654e668d457758110abec33dfbd3ba5 ] I think this was an abstraction back from when kfd supported both radeon and amdgpu. Since we just support amdgpu now, there is no more need for this and we can use the amdgpu structures directly. This also avoids having the kfd_cu_info structures on the stack when inlining which can blow up the stack. Cc: Arnd Bergmann <arnd@kernel.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Stable-dep-of: 438b39ac74e2 ("drm/amdkfd: pause autosuspend when creating pdd") Signed-off-by: Sasha Levin <sashal@kernel.org>
2025-01-02drm/amdkfd: reduce stack size in kfd_topology_add_device()Alex Deucher1-4/+9
[ Upstream commit 4ff91f218547bfc3d230c00e46725b71a625acbc ] kfd_topology.c:2082:1: warning: the frame size of 1440 bytes is larger than 1024 bytes Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2866 Cc: Arnd Bergmann <arnd@kernel.org> Acked-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Stable-dep-of: 438b39ac74e2 ("drm/amdkfd: pause autosuspend when creating pdd") Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-12-09drm/amdkfd: Use the correct wptr sizeLijo Lazar1-1/+1
commit cdc6705f98ea3f854a60ba8c9b19228e197ae384 upstream. Write pointer could be 32-bit or 64-bit. Use the correct size during initialization. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-12-09drm/amdkfd: Fix wrong usage of INIT_WORK()Yuan Can1-2/+3
[ Upstream commit 21cae8debc6a1d243f64fa82cd1b41cb612b5c61 ] In kfd_procfs_show(), the sdma_activity_work_handler is a local variable and the sdma_activity_work_handler.sdma_activity_work should initialize with INIT_WORK_ONSTACK() instead of INIT_WORK(). Fixes: 32cb59f31362 ("drm/amdkfd: Track SDMA utilization per process") Signed-off-by: Yuan Can <yuancan@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> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-11-17drm/amdkfd: Accounting pdd vram_usage for svmPhilip Yang4-6/+32
[ Upstream commit 68d26c10ef503175df3142db6fcd75dd94860592 ] Process device data pdd->vram_usage is read by rocm-smi via sysfs, this is currently missing the svm_bo usage accounting, so "rocm-smi --showpids" per process VRAM usage report is incorrect. Add pdd->vram_usage accounting when svm_bo allocation and release, change to atomic64_t type because it is updated outside process mutex now. 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> (cherry picked from commit 98c0b0efcc11f2a5ddf3ce33af1e48eedf808b04) Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-10-10drm/amdkfd: Fix resource leak in criu restore queueJesse Zhang1-0/+1
[ Upstream commit aa47fe8d3595365a935921a90d00bc33ee374728 ] To avoid memory leaks, release q_extra_data when exiting the restore queue. v2: Correct the proto (Alex) Signed-off-by: Jesse Zhang <jesse.zhang@amd.com> Reviewed-by: Tim Huang <tim.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-10-10drm/amdkfd: amdkfd_free_gtt_mem clear the correct pointerPhilip Yang6-8/+8
[ Upstream commit c86ad39140bbcb9dc75a10046c2221f657e8083b ] Pass pointer reference to amdgpu_bo_unref to clear the correct pointer, otherwise amdgpu_bo_unref clear the local variable, the original pointer not set to NULL, this could cause use-after-free bug. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-09-08drm/amdgpu: add lock in kfd_process_dequeue_from_deviceYunxiang Li1-2/+7
[ Upstream commit d225960c2330e102370815367b877baaf8bb8b5d ] We need to take the reset domain lock before talking to MES. While in this case we can take the lock inside the mes helper. We can't do so for most other mes helpers since they are used during reset. So for consistency sake we add the lock here. Signed-off-by: Yunxiang Li <Yunxiang.Li@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-09-08drm/amdkfd: Reconcile the definition and use of oem_id in struct ↵Michael Chen3-5/+5
kfd_topology_device [ Upstream commit 10f624ef239bd136cdcc5bbc626157a57b938a31 ] Currently oem_id is defined as uint8_t[6] and casted to uint64_t* in some use case. This would lead code scanner to complain about access beyond. Re-define it in union to enforce 8-byte size and alignment to avoid potential issue. Signed-off-by: Michael Chen <michael.chen@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-09-08drm/amdkfd: Check debug trap enable before write dbg_ev_fileLin.Cao1-1/+3
[ Upstream commit 547033b593063eb85bfdf9b25a5f1b8fd1911be2 ] In interrupt context, write dbg_ev_file will be run by work queue. It will cause write dbg_ev_file execution after debug_trap_disable, which will cause NULL pointer access. v2: cancel work "debug_event_workarea" before set dbg_ev_file as NULL. Signed-off-by: Lin.Cao <lincao12@amd.com> Reviewed-by: Jonathan Kim <jonathan.kim@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-08-29drm/amdkfd: reserve the BO before validating itLang Yu1-1/+3
[ Upstream commit 0c93bd49576677ae1a18817d5ec000ef031d5187 ] Fix a warning. v2: Avoid unmapping attachment repeatedly when ERESTARTSYS. v3: Lock the BO before accessing ttm->sg to avoid race conditions.(Felix) [ 41.708711] WARNING: CPU: 0 PID: 1463 at drivers/gpu/drm/ttm/ttm_bo.c:846 ttm_bo_validate+0x146/0x1b0 [ttm] [ 41.708989] Call Trace: [ 41.708992] <TASK> [ 41.708996] ? show_regs+0x6c/0x80 [ 41.709000] ? ttm_bo_validate+0x146/0x1b0 [ttm] [ 41.709008] ? __warn+0x93/0x190 [ 41.709014] ? ttm_bo_validate+0x146/0x1b0 [ttm] [ 41.709024] ? report_bug+0x1f9/0x210 [ 41.709035] ? handle_bug+0x46/0x80 [ 41.709041] ? exc_invalid_op+0x1d/0x80 [ 41.709048] ? asm_exc_invalid_op+0x1f/0x30 [ 41.709057] ? amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x2c/0x80 [amdgpu] [ 41.709185] ? ttm_bo_validate+0x146/0x1b0 [ttm] [ 41.709197] ? amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x2c/0x80 [amdgpu] [ 41.709337] ? srso_alias_return_thunk+0x5/0x7f [ 41.709346] kfd_mem_dmaunmap_attachment+0x9e/0x1e0 [amdgpu] [ 41.709467] amdgpu_amdkfd_gpuvm_dmaunmap_mem+0x56/0x80 [amdgpu] [ 41.709586] kfd_ioctl_unmap_memory_from_gpu+0x1b7/0x300 [amdgpu] [ 41.709710] kfd_ioctl+0x1ec/0x650 [amdgpu] [ 41.709822] ? __pfx_kfd_ioctl_unmap_memory_from_gpu+0x10/0x10 [amdgpu] [ 41.709945] ? srso_alias_return_thunk+0x5/0x7f [ 41.709949] ? tomoyo_file_ioctl+0x20/0x30 [ 41.709959] __x64_sys_ioctl+0x9c/0xd0 [ 41.709967] do_syscall_64+0x3f/0x90 [ 41.709973] entry_SYSCALL_64_after_hwframe+0x6e/0xd8 Fixes: 101b8104307e ("drm/amdkfd: Move dma unmapping after TLB flush") Signed-off-by: Lang Yu <Lang.Yu@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-08-29drm/amdkfd: Move dma unmapping after TLB flushPhilip Yang1-8/+12
[ Upstream commit 101b8104307eac734f2dfa4d3511430b0b631c73 ] Otherwise GPU may access the stale mapping and generate IOMMU IO_PAGE_FAULT. Move this to inside p->mutex to prevent multiple threads mapping and unmapping concurrently race condition. After kfd_mem_dmaunmap_attachment is removed from unmap_bo_from_gpuvm, kfd_mem_dmaunmap_attachment is called if failed to map to GPUs, and before free the mem attachment in case failed to unmap from GPUs. 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> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-08-03drm/amdkfd: Fix CU Masking for GFX 9.4.3Mukul Joshi1-1/+1
[ Upstream commit 85cf43c554e438e2e12b0fe109688c9533e4d93f ] We are incorrectly passing the first XCC's MQD when updating CU masks for other XCCs in the partition. Fix this by passing the MQD for the XCC currently being updated with CU mask to update_cu_mask function. Fixes: fc6efed2c728 ("drm/amdkfd: Update CU masking for GFX 9.4.3") Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-06-16Revert "drm/amdkfd: fix gfx_target_version for certain 11.0.3 devices"Alex Deucher1-9/+2
commit dd2b75fd9a79bf418e088656822af06fc253dbe3 upstream. This reverts commit 28ebbb4981cb1fad12e0b1227dbecc88810b1ee8. Revert this commit as apparently the LLVM code to take advantage of this never landed. Reviewed-by: Feifei Xu <Feifei.Xu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: Feifei Xu <feifei.xu@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-06-12drm/amdkfd: Flush the process wq before creating a kfd_processLancelot SIX1-0/+8
[ Upstream commit f5b9053398e70a0c10aa9cb4dd5910ab6bc457c5 ] There is a race condition when re-creating a kfd_process for a process. This has been observed when a process under the debugger executes exec(3). In this scenario: - The process executes exec. - This will eventually release the process's mm, which will cause the kfd_process object associated with the process to be freed (kfd_process_free_notifier decrements the reference count to the kfd_process to 0). This causes kfd_process_ref_release to enqueue kfd_process_wq_release to the kfd_process_wq. - The debugger receives the PTRACE_EVENT_EXEC notification, and tries to re-enable AMDGPU traps (KFD_IOC_DBG_TRAP_ENABLE). - When handling this request, KFD tries to re-create a kfd_process. This eventually calls kfd_create_process and kobject_init_and_add. At this point the call to kobject_init_and_add can fail because the old kfd_process.kobj has not been freed yet by kfd_process_wq_release. This patch proposes to avoid this race by making sure to drain kfd_process_wq before creating a new kfd_process object. This way, we know that any cleanup task is done executing when we reach kobject_init_and_add. Signed-off-by: Lancelot SIX <lancelot.six@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-06-12drm/amdkfd: Add VRAM accounting for SVM migrationMukul Joshi2-2/+16
[ Upstream commit 1e214f7faaf5d842754cd5cfcd76308bfedab3b5 ] Do VRAM accounting when doing migrations to vram to make sure there is enough available VRAM and migrating to VRAM doesn't evict other possible non-unified memory BOs. If migrating to VRAM fails, driver can fall back to using system memory seamlessly. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-05-17drm/amdkfd: don't allow mapping the MMIO HDP page with large pagesAlex Deucher1-2/+5
commit be4a2a81b6b90d1a47eaeaace4cc8e2cb57b96c7 upstream. We don't get the right offset in that case. The GPU has an unused 4K area of the register BAR space into which you can remap registers. We remap the HDP flush registers into this space to allow userspace (CPU or GPU) to flush the HDP when it updates VRAM. However, on systems with >4K pages, we end up exposing PAGE_SIZE of MMIO space. Fixes: d8e408a82704 ("drm/amdkfd: Expose HDP registers to user space") Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-05-17amd/amdkfd: sync all devices to wait all processes being evictedZhigang Luo1-11/+6
[ Upstream commit d06af584be5a769d124b7302b32a033e9559761d ] If there are more than one device doing reset in parallel, the first device will call kfd_suspend_all_processes() to evict all processes on all devices, this call takes time to finish. other device will start reset and recover without waiting. if the process has not been evicted before doing recover, it will be restored, then caused page fault. Signed-off-by: Zhigang Luo <Zhigang.Luo@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-05-17drm/amdkfd: range check cp bad op exception interruptsJonathan Kim3-3/+6
[ Upstream commit 0cac183b98d8a8c692c98e8dba37df15a9e9210d ] Due to a CP interrupt bug, bad packet garbage exception codes are raised. Do a range check so that the debugger and runtime do not receive garbage codes. Update the user api to guard exception code type checking as well. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Tested-by: Jesse Zhang <jesse.zhang@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-05-17drm/amdkfd: Check cgroup when returning DMABuf infoMukul Joshi1-2/+2
[ Upstream commit 9d7993a7ab9651afd5fb295a4992e511b2b727aa ] Check cgroup permissions when returning DMA-buf info and based on cgroup info return the GPU id of the GPU that have access to the BO. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-04-27drm/amdkfd: Fix memory leak in create_process failureFelix Kuehling1-2/+2
commit 18921b205012568b45760753ad3146ddb9e2d4e2 upstream. Fix memory leak due to a leaked mmget reference on an error handling code path that is triggered when attempting to create KFD processes while a GPU reset is in progress. Fixes: 0ab2d7532b05 ("drm/amdkfd: prepare per-process debug enable and disable") CC: Xiaogang Chen <xiaogang.chen@amd.com> Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Tested-by: Harish Kasiviswanthan <Harish.Kasiviswanthan@amd.com> Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-04-17drm/amdkfd: Reset GPU on queue preemption failureHarish Kasiviswanathan1-0/+1
commit 8bdfb4ea95ca738d33ef71376c21eba20130f2eb upstream. Currently, with F32 HWS GPU reset is only when unmap queue fails. However, if compute queue doesn't repond to preemption request in time unmap will return without any error. In this case, only preemption error is logged and Reset is not triggered. Call GPU reset in this case also. Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-04-13amdkfd: use calloc instead of kzalloc to avoid integer overflowDave Airlie1-2/+2
commit 3b0daecfeac0103aba8b293df07a0cbaf8b43f29 upstream. This uses calloc instead of doing the multiplication which might overflow. Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie <airlied@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-04-03drm/amdkfd: fix TLB flush after unmap for GFX9.4.2Eric Huang1-1/+1
commit 1210e2f1033dc56b666c9f6dfb761a2d3f9f5d6c upstream. TLB flush after unmap accidentially was removed on gfx9.4.2. It is to add it back. Signed-off-by: Eric Huang <jinhuieric.huang@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-03-01drm/amdkfd: Use correct drm device for cgroup permission checkMukul Joshi1-2/+7
[ Upstream commit 4119734e06a7f30e7e8eb666692a58b85dca0269 ] On GFX 9.4.3, for a given KFD node, fetch the correct drm device from XCP manager when checking for cgroup permissions. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-05drm/amdkfd: only flush mes process context if mes support is thereJonathan Kim1-1/+2
[ Upstream commit 24149412dfc71f7f4a54868702e9145e396263d3 ] Fix up on mes process context flush to prevent non-mes devices from spamming error messages or running into undefined behaviour during process termination. Fixes: bd33bb1409b4 ("drm/amdkfd: fix mes set shader debugger process management") Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Eric Huang <jinhuieric.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-05drm/amdkfd: Fix 'node' NULL check in 'svm_range_get_range_boundaries()'Srinivasan Shanmugam1-5/+5
[ Upstream commit d7a254fad873775ce6c32b77796c81e81e6b7f2e ] Range interval [start, last] is ordered by rb_tree, rb_prev, rb_next return value still needs NULL check, thus modified from "node" to "rb_node". Fixes the below: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_svm.c:2691 svm_range_get_range_boundaries() warn: can 'node' even be NULL? Suggested-by: Philip Yang <Philip.Yang@amd.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-05drm/amdkfd: Fix lock dependency warning with srcuPhilip Yang1-2/+4
[ Upstream commit 2a9de42e8d3c82c6990d226198602be44f43f340 ] ====================================================== WARNING: possible circular locking dependency detected 6.5.0-kfd-yangp #2289 Not tainted ------------------------------------------------------ kworker/0:2/996 is trying to acquire lock: (srcu){.+.+}-{0:0}, at: __synchronize_srcu+0x5/0x1a0 but task is already holding lock: ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}, at: process_one_work+0x211/0x560 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #3 ((work_completion)(&svms->deferred_list_work)){+.+.}-{0:0}: __flush_work+0x88/0x4f0 svm_range_list_lock_and_flush_work+0x3d/0x110 [amdgpu] svm_range_set_attr+0xd6/0x14c0 [amdgpu] kfd_ioctl+0x1d1/0x630 [amdgpu] __x64_sys_ioctl+0x88/0xc0 -> #2 (&info->lock#2){+.+.}-{3:3}: __mutex_lock+0x99/0xc70 amdgpu_amdkfd_gpuvm_restore_process_bos+0x54/0x740 [amdgpu] restore_process_helper+0x22/0x80 [amdgpu] restore_process_worker+0x2d/0xa0 [amdgpu] process_one_work+0x29b/0x560 worker_thread+0x3d/0x3d0 -> #1 ((work_completion)(&(&process->restore_work)->work)){+.+.}-{0:0}: __flush_work+0x88/0x4f0 __cancel_work_timer+0x12c/0x1c0 kfd_process_notifier_release_internal+0x37/0x1f0 [amdgpu] __mmu_notifier_release+0xad/0x240 exit_mmap+0x6a/0x3a0 mmput+0x6a/0x120 do_exit+0x322/0xb90 do_group_exit+0x37/0xa0 __x64_sys_exit_group+0x18/0x20 do_syscall_64+0x38/0x80 -> #0 (srcu){.+.+}-{0:0}: __lock_acquire+0x1521/0x2510 lock_sync+0x5f/0x90 __synchronize_srcu+0x4f/0x1a0 __mmu_notifier_release+0x128/0x240 exit_mmap+0x6a/0x3a0 mmput+0x6a/0x120 svm_range_deferred_list_work+0x19f/0x350 [amdgpu] process_one_work+0x29b/0x560 worker_thread+0x3d/0x3d0 other info that might help us debug this: Chain exists of: srcu --> &info->lock#2 --> (work_completion)(&svms->deferred_list_work) Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&svms->deferred_list_work)); lock(&info->lock#2); lock((work_completion)(&svms->deferred_list_work)); sync(srcu); 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> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-05drm/amdkfd: Fix lock dependency warningFelix Kuehling1-16/+10
[ Upstream commit 47bf0f83fc86df1bf42b385a91aadb910137c5c9 ] ====================================================== WARNING: possible circular locking dependency detected 6.5.0-kfd-fkuehlin #276 Not tainted ------------------------------------------------------ kworker/8:2/2676 is trying to acquire lock: ffff9435aae95c88 ((work_completion)(&svm_bo->eviction_work)){+.+.}-{0:0}, at: __flush_work+0x52/0x550 but task is already holding lock: ffff9435cd8e1720 (&svms->lock){+.+.}-{3:3}, at: svm_range_deferred_list_work+0xe8/0x340 [amdgpu] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #2 (&svms->lock){+.+.}-{3:3}: __mutex_lock+0x97/0xd30 kfd_ioctl_alloc_memory_of_gpu+0x6d/0x3c0 [amdgpu] kfd_ioctl+0x1b2/0x5d0 [amdgpu] __x64_sys_ioctl+0x86/0xc0 do_syscall_64+0x39/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd -> #1 (&mm->mmap_lock){++++}-{3:3}: down_read+0x42/0x160 svm_range_evict_svm_bo_worker+0x8b/0x340 [amdgpu] process_one_work+0x27a/0x540 worker_thread+0x53/0x3e0 kthread+0xeb/0x120 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x11/0x20 -> #0 ((work_completion)(&svm_bo->eviction_work)){+.+.}-{0:0}: __lock_acquire+0x1426/0x2200 lock_acquire+0xc1/0x2b0 __flush_work+0x80/0x550 __cancel_work_timer+0x109/0x190 svm_range_bo_release+0xdc/0x1c0 [amdgpu] svm_range_free+0x175/0x180 [amdgpu] svm_range_deferred_list_work+0x15d/0x340 [amdgpu] process_one_work+0x27a/0x540 worker_thread+0x53/0x3e0 kthread+0xeb/0x120 ret_from_fork+0x31/0x50 ret_from_fork_asm+0x11/0x20 other info that might help us debug this: Chain exists of: (work_completion)(&svm_bo->eviction_work) --> &mm->mmap_lock --> &svms->lock Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&svms->lock); lock(&mm->mmap_lock); lock(&svms->lock); lock((work_completion)(&svm_bo->eviction_work)); I believe this cannot really lead to a deadlock in practice, because svm_range_evict_svm_bo_worker only takes the mmap_read_lock if the BO refcount is non-0. That means it's impossible that svm_range_bo_release is running concurrently. However, there is no good way to annotate this. To avoid the problem, take a BO reference in svm_range_schedule_evict_svm_bo instead of in the worker. That way it's impossible for a BO to get freed while eviction work is pending and the cancel_work_sync call in svm_range_bo_release can be eliminated. v2: Use svm_bo_ref_unless_zero and explained why that's safe. Also removed redundant checks that are already done in amdkfd_fence_enable_signaling. Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-05drm/amdkfd: Fix iterator used outside loop in 'kfd_add_peer_prop()'Srinivasan Shanmugam1-11/+13
[ Upstream commit b1a428b45dc7e47c7acc2ad0d08d8a6dda910c4c ] Fix the following about iterator use: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1456 kfd_add_peer_prop() warn: iterator used outside loop: 'iolink3' Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-05drm/amdkfd: fix mes set shader debugger process managementJonathan Kim1-0/+1
[ Upstream commit bd33bb1409b494558a2935f7bbc7842def957fcd ] MES provides the driver a call to explicitly flush stale process memory within the MES to avoid a race condition that results in a fatal memory violation. When SET_SHADER_DEBUGGER is called, the driver passes a memory address that represents a process context address MES uses to keep track of future per-process calls. Normally, MES will purge its process context list when the last queue has been removed. The driver, however, can call SET_SHADER_DEBUGGER regardless of whether a queue has been added or not. If SET_SHADER_DEBUGGER has been called with no queues as the last call prior to process termination, the passed process context address will still reside within MES. On a new process call to SET_SHADER_DEBUGGER, the driver may end up passing an identical process context address value (based on per-process gpu memory address) to MES but is now pointing to a new allocated buffer object during KFD process creation. Since the MES is unaware of this, access of the passed address points to the stale object within MES and triggers a fatal memory violation. The solution is for KFD to explicitly flush the process context address from MES on process termination. Note that the flush call and the MES debugger calls use the same MES interface but are separated as KFD calls to avoid conflicting with each other. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Tested-by: Alice Wong <shiwei.wong@amd.com> Reviewed-by: Eric Huang <jinhuieric.huang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-01drm/amdgpu/gfx11: set UNORD_DISPATCH in compute MQDsAlex Deucher1-0/+1
[ Upstream commit 3380fcad2c906872110d31ddf7aa1fdea57f9df6 ] This needs to be set to 1 to avoid a potential deadlock in the GC 10.x and newer. On GC 9.x and older, this needs to be set to 0. This can lead to hangs in some mixed graphics and compute workloads. Updated firmware is also required for AQL. Reviewed-by: Feifei Xu <Feifei.Xu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-02-01drm/amdgpu/gfx10: set UNORD_DISPATCH in compute MQDsAlex Deucher1-0/+1
[ Upstream commit 03ff6d7238b77e5fb2b85dc5fe01d2db9eb893bd ] This needs to be set to 1 to avoid a potential deadlock in the GC 10.x and newer. On GC 9.x and older, this needs to be set to 0. This can lead to hangs in some mixed graphics and compute workloads. Updated firmware is also required for AQL. Reviewed-by: Feifei Xu <Feifei.Xu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-01-26drm/amdkfd: fixes for HMM mem allocationDafna Hirschfeld1-3/+3
[ Upstream commit 02eed83abc1395a1207591aafad9bcfc5cb1abcb ] Fix err return value and reset pgmap->type after checking it. Fixes: c83dee9b6394 ("drm/amdkfd: add SPM support for SVM") Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Dafna Hirschfeld <dhirschfeld@habana.ai> Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-01-26Revert "drm/amdkfd: Relocate TBA/TMA to opposite side of VM hole"Kaibo Ma1-13/+13
commit 0f35b0a7b8fa402adbffa2565047cdcc4c480153 upstream. That commit causes NULL pointer dereferences in dmesgs when running applications using ROCm, including clinfo, blender, and PyTorch, since v6.6.1. Revert it to fix blender again. This reverts commit 96c211f1f9ef82183493f4ceed4e347b52849149. Closes: https://github.com/ROCm/ROCm/issues/2596 Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2991 Reviewed-by: Jay Cornwall <jay.cornwall@amd.com> Signed-off-by: Kaibo Ma <ent3rm4n@gmail.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2024-01-26drm/amdkfd: Confirm list is non-empty before utilizing list_first_entry in ↵Srinivasan Shanmugam1-9/+12
kfd_topology.c [ Upstream commit 499839eca34ad62d43025ec0b46b80e77065f6d8 ] Before using list_first_entry, make sure to check that list is not empty, if list is empty return -ENODATA. Fixes the below: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1347 kfd_create_indirect_link_prop() warn: can 'gpu_link' even be NULL? drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1428 kfd_add_peer_prop() warn: can 'iolink1' even be NULL? drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_topology.c:1433 kfd_add_peer_prop() warn: can 'iolink2' even be NULL? Fixes: 0f28cca87e9a ("drm/amdkfd: Extend KFD device topology to surface peer-to-peer links") Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Suggested-by: Felix Kuehling <Felix.Kuehling@amd.com> Suggested-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-01-26drm/amdkfd: Fix type of 'dbg_flags' in 'struct kfd_process'Srinivasan Shanmugam1-1/+1
[ Upstream commit 217e85f97031791fb48a2d374c7bdcf439365b21 ] dbg_flags looks to be defined with incorrect data type; to process multiple debug flag options, and hence defined dbg_flags as u32. Fixes the below: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_packet_manager_v9.c:117 pm_map_process_aldebaran() warn: maybe use && instead of & Fixes: 0de4ec9a0353 ("drm/amdgpu: prepare map process for multi-process debug devices") Suggested-by: Lijo Lazar <lijo.lazar@amd.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Christian König <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-01-20drm/amdkfd: svm range always mapped flag not working on APUPhilip Yang1-6/+12
[ Upstream commit ebab8c3eb6a6515dc14cd93fc29dd287709da6d3 ] On gfx943 APU there is no VRAM and page migration, queue CWSR area, svm range with always mapped flag, is not mapped to GPU correctly. This works fine if retry fault on CWSR area can be recovered, but could cause deadlock if there is another retry fault recover waiting for CWSR to finish. Fix this by mapping svm range with always mapped flag to GPU with ACCESS attribute if XNACK ON. There is side effect, because all GPUs have ACCESS attribute by default on new svm range with XNACK on, the CWSR area will be mapped to all GPUs after this change. This side effect will be fixed with Thunk change to set CWSR svm range with ACCESS_IN_PLACE attribute on the GPU that user queue is created. 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> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-01-20drm/amdkfd: Free gang_ctx_bo and wptr_bo in pqm_uninitZhenGuo Yin1-21/+33
[ Upstream commit 72838777aa38352e20301e123b97110c456cd38e ] [Why] Memory leaks of gang_ctx_bo and wptr_bo. [How] Free gang_ctx_bo and wptr_bo in pqm_uninit. v2: add a common function pqm_clean_queue_resource to free queue's resources. v3: reset pdd->pqd.num_gws when destorying GWS queue. Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: ZhenGuo Yin <zhenguo.yin@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2024-01-20drm/amdkfd: Use common function for IP version checkMukul Joshi1-1/+1
[ Upstream commit 2f86bf79b63dbe6963ebc647b77a5f576a906b40 ] KFD_GC_VERSION was recently updated to use a new function for IP version checks. As a result, use KFD_GC_VERSION as the common function for all IP version checks in KFD. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-12-13drm/amdkfd: get doorbell's absolute offset based on the db_sizeArvind Yadav3-4/+12
[ Upstream commit 367a0af43373d4f791cc8b466a659ecf5aa52377 ] Here, Adding db_size in byte to find the doorbell's absolute offset for both 32-bit and 64-bit doorbell sizes. So that doorbell offset will be aligned based on the doorbell size. v2: - Addressed the review comment from Felix. v3: - Adding doorbell_size as parameter to get db absolute offset. v4: Squash the two patches into one. Cc: Christian Koenig <christian.koenig@amd.com> Cc: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com> Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-11-28drm/amdkfd: Fix shift out-of-bounds issueJesse Zhang1-1/+1
[ Upstream commit 282c1d793076c2edac6c3db51b7e8ed2b41d60a5 ] [ 567.613292] shift exponent 255 is too large for 64-bit type 'long unsigned int' [ 567.614498] CPU: 5 PID: 238 Comm: kworker/5:1 Tainted: G OE 6.2.0-34-generic #34~22.04.1-Ubuntu [ 567.614502] Hardware name: AMD Splinter/Splinter-RPL, BIOS WS43927N_871 09/25/2023 [ 567.614504] Workqueue: events send_exception_work_handler [amdgpu] [ 567.614748] Call Trace: [ 567.614750] <TASK> [ 567.614753] dump_stack_lvl+0x48/0x70 [ 567.614761] dump_stack+0x10/0x20 [ 567.614763] __ubsan_handle_shift_out_of_bounds+0x156/0x310 [ 567.614769] ? srso_alias_return_thunk+0x5/0x7f [ 567.614773] ? update_sd_lb_stats.constprop.0+0xf2/0x3c0 [ 567.614780] svm_range_split_by_granularity.cold+0x2b/0x34 [amdgpu] [ 567.615047] ? srso_alias_return_thunk+0x5/0x7f [ 567.615052] svm_migrate_to_ram+0x185/0x4d0 [amdgpu] [ 567.615286] do_swap_page+0x7b6/0xa30 [ 567.615291] ? srso_alias_return_thunk+0x5/0x7f [ 567.615294] ? __free_pages+0x119/0x130 [ 567.615299] handle_pte_fault+0x227/0x280 [ 567.615303] __handle_mm_fault+0x3c0/0x720 [ 567.615311] handle_mm_fault+0x119/0x330 [ 567.615314] ? lock_mm_and_find_vma+0x44/0x250 [ 567.615318] do_user_addr_fault+0x1a9/0x640 [ 567.615323] exc_page_fault+0x81/0x1b0 [ 567.615328] asm_exc_page_fault+0x27/0x30 [ 567.615332] RIP: 0010:__get_user_8+0x1c/0x30 Signed-off-by: Jesse Zhang <jesse.zhang@amd.com> Suggested-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Yifan Zhang <yifan1.zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-11-28drm/amdkfd: Fix a race condition of vram buffer unref in svm codeXiaogang Chen1-2/+9
[ Upstream commit 709c348261618da7ed89d6c303e2ceb9e453ba74 ] prange->svm_bo unref can happen in both mmu callback and a callback after migrate to system ram. Both are async call in different tasks. Sync svm_bo unref operation to avoid random "use-after-free". Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com> Tested-by: Jesse Zhang <Jesse.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-11-28drm/amdkfd: ratelimited SQ interrupt messagesHarish Kasiviswanathan3-9/+9
[ Upstream commit 37fb87910724f21a1f27a75743d4f9accdee77fb ] No functional change. Use ratelimited version of pr_ to avoid overflowing of dmesg buffer Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: Philip Yang <philip.yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-11-20drm/amdkfd: Handle errors from svm validate and mapPhilip Yang2-44/+39
[ Upstream commit eb3c357bcb286e89386e89302061fe717fe4e562 ] If new range is splited to multiple pranges with max_svm_range_pages alignment and added to update_list, svm validate and map should keep going after error to make sure prange->mapped_to_gpu flag is up to date for the whole range. svm validate and map update set prange->mapped_to_gpu after mapping to GPUs successfully, otherwise clear prange->mapped_to_gpu flag (for update mapping case) instead of setting error flag, we can remove the redundant error flag to simpliy code. Refactor to remove goto and update prange->mapped_to_gpu flag inside svm_range_lock, to guarant we always evict queues or unmap from GPUs if there are invalid ranges. After svm validate and map return error -EAGIN, the caller retry will update the mapping for the whole range again. Fixes: c22b04407097 ("drm/amdkfd: flag added to handle errors from svm validate and map") Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Tested-by: James Zhu <james.zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
2023-11-20drm/amdkfd: Remove svm range validated_once flagPhilip Yang2-4/+1
[ Upstream commit c99b16128082de519975aa147d9da3e40380de67 ] The validated_once flag is not used after the prefault was removed, The prefault was needed to ensure validate all system memory pages at least once before mapping or migrating the range to GPU. 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> Stable-dep-of: eb3c357bcb28 ("drm/amdkfd: Handle errors from svm validate and map") Signed-off-by: Sasha Levin <sashal@kernel.org>
generated by cgit v1.2.3 (git 2.39.0) at 2026-05-13 11:19:04 +0300