summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdkfd
AgeCommit message (Collapse)Author
2024-12-10drm/amd: define gc ip version local variableAlex Sierra
For better readability. Also leftover orphaned code. Signed-off-by: Alex Sierra <alex.sierra@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Harish Kasiviswanathan <harish.kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-12-10drm/amdkfd: Differentiate logging message for driver oversubscriptionXiaogang Chen
To have user better understand the causes triggering runlist oversubscription. No function change. Signed-off-by: Xiaogang Chen <xiaogang.chen@amd.com> Reviewed-by: Harish Kasiviswanathan <harish.kasiviswanathan@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-12-10drm/amdgpu: Prefer RAS recovery for scheduler hangLijo Lazar
Before scheduling a recovery due to scheduler/job hang, check if a RAS error is detected. If so, choose RAS recovery to handle the situation. A scheduler/job hang could be the side effect of a RAS error. In such cases, it is required to go through the RAS error recovery process. A RAS error recovery process in certains cases also could avoid a full device device reset. An error state is maintained in RAS context to detect the block affected. Fatal Error state uses unused block id. Set the block id when error is detected. If the interrupt handler detected a poison error, it's not required to look for a fatal error. Skip fatal error checking in such cases. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-12-10drm/amdkfd: pause autosuspend when creating pddJesse.zhang@amd.com
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
2024-12-10drm/amdkfd: hard-code MALL cacheline size for gfx11, gfx12Harish Kasiviswanathan
This information is not available in ip discovery table. Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: David Belanger <david.belanger@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2024-12-10drm/amdkfd: hard-code cacheline size for gfx11Harish Kasiviswanathan
This information is not available in ip discovery table. Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: David Belanger <david.belanger@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2024-12-10drm/amdkfd: Dereference null return valueAndrew Martin
In the function pqm_uninit there is a call-assignment of "pdd = kfd_get_process_device_data" which could be null, and this value was later dereferenced without checking. Fixes: fb91065851cd ("drm/amdkfd: Refactor queue wptr_bo GART mapping") Signed-off-by: Andrew Martin <Andrew.Martin@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2024-12-05drm/amdkfd: Correct the migration DMA map directionPrike Liang
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>
2024-12-02drm/amdkfd: hard-code cacheline for gc943,gc944David Yat Sin
Cacheline size is not available in IP discovery for gc943,gc944. Signed-off-by: David Yat Sin <David.YatSin@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org
2024-12-02drm/amdkfd: add MEC version that supports no PCIe atomics for GFX12Sreekant Somasekharan
Add MEC version from which alternate support for no PCIe atomics is provided so that device is not skipped during KFD device init in GFX1200/GFX1201. Signed-off-by: Sreekant Somasekharan <sreekant.somasekharan@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org # 6.11.x
2024-11-21drm/amdkfd: Use the correct wptr sizeLijo Lazar
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
2024-11-20drm/amdkfd: make sure ring buffer is flushed before update wptrVictor Zhao
In a consecutive packet submission, for example unmap and query status, when CP is reading wptr caused by unmap packet doorbell ring, if in some case CP operates slower (e.g. doorbell_mode=1) and wptr has been updated to next packet (query status), but the query status packet content has not been flushed to memory yet, it will cause CP fetched stalled data. Adding mb to ensure ring buffer has been updated before updating wptr. Also adding a mb to ensure wptr updated before doorbell ring. Signed-off-by: Victor Zhao <Victor.Zhao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-11-11drm/amd/amdkfd: add/remove kfd queues on start/stop KFD schedulingShaoyun Liu
Add back kfd queues in start scheduling that originally been removed on stop scheduling. Signed-off-by: Shaoyun Liu <shaoyun.liu@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-11-11drm/amdkfd: change kfd process kref count at creationXiaogang Chen
kfd process kref count(process->ref) is initialized to 1 by kref_init. After it is created not need to increase its kref. Instad add kfd process kref at kfd process mmu notifier allocation since we already decrease the kref at free_notifier of mmu_notifier_ops, so pair them. When user process opens kfd node multiple times the kfd process kref is increased each time to balance with kfd node close operation. 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>
2024-11-08drm/amdkfd: Fix wrong usage of INIT_WORK()Yuan Can
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>
2024-11-08drm/amdkfd: remove gfx 12 trap handler page size capJonathan Kim
GFX 12 does not require a page size cap for the trap handler because it does not require a CWSR work around like GFX 11 did. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: David Belanger <david.belanger@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-11-04drm/amdkfd: Use dynamic allocation for CU occupancy array in ↵Srinivasan Shanmugam
'kfd_get_cu_occupancy()' The `kfd_get_cu_occupancy` function previously declared a large `cu_occupancy` array as a local variable, which could lead to stack overflows due to excessive stack usage. This commit replaces the static array allocation with dynamic memory allocation using `kcalloc`, thereby reducing the stack size. This change avoids the risk of stack overflows in kernel space, in scenarios where `AMDGPU_MAX_QUEUES` is large. The allocated memory is freed using `kfree` before the function returns to prevent memory leaks. Fixes the below with gcc W=1: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_process.c: In function ‘kfd_get_cu_occupancy’: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_process.c:322:1: warning: the frame size of 1056 bytes is larger than 1024 bytes [-Wframe-larger-than=] 322 | } | ^ Fixes: 6ae9e1aba97e ("drm/amdkfd: Update logic for CU occupancy calculations") Cc: Harish Kasiviswanathan <Harish.Kasiviswanathan@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> Suggested-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Mukul Joshi <mukul.joshi@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-11-04drm/amdkfd: add an interface to query whether is KFD is activeAlex Deucher
Add an interface to query whether KFD has any active queues. v2: fix build issues Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-28drm/amdkfd: flag per-queue reset support for gfx9Jonathan Kim
Flag KFD support for per-queue reset on GFX9 devices. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Harish Kasiviswanathan <harish.kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-24drm/amdkfd: sever xgmi io link if host driver has disable sharingJonathan Kim
Host drivers can create partial hives per guest by disabling xgmi sharing between certain peers in the main hive. Typically, these partial hives are fully connected per guest session. In the event that the host makes a mistake by adding a non-shared node to a guest session, have the KFD reflect sharing disabled by severing the IO link. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Tested-by: James Yao <yiqing.yao@amd.com> Reviewed-by: Harish Kasiviswanathan <harish.kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-24drm/amdkfd: remove extra use of volatileVictor Zhao
as the adding of mb() should be sufficient in function unmap_queues_cpsch, remove the add of volatile type as recommended Signed-off-by: Victor Zhao <Victor.Zhao@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-22Revert "drm/amdkfd: SMI report dropped event count"Alex Deucher
This reverts commit a3ab2d45b9887ee609cd3bea39f668236935774c. The userspace side for this code is not ready yet so revert for now. Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: Philip Yang <Philip.Yang@amd.com>
2024-10-22drm/amdkfd: fix the hang caused by the write reorder to fence_addrVictor Zhao
make sure KFD_FENCE_INIT write to fence_addr before pm_send_query_status called, to avoid qcm fence timeout caused by incorrect ordering. Signed-off-by: Victor Zhao <Victor.Zhao@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-15drm/amdkfd: Accounting pdd vram_usage for svmPhilip Yang
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>
2024-10-07drm/amdkfd: SMI report dropped event countPhilip Yang
Add new SMI event to report the dropped event count. When the event kfifo is full, drop count is not zero, or no enough space left to store the event message, increase drop count. After reading event out from kfifo, if event was dropped, drop_count is not zero, generate a dropped event record and reset drop count to zero. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: James Zhu <James.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-07drm/amdkfd: Copy wave state only for compute queuePhilip Yang
get_wave_state is not defined for sdma queue, copy_context_work_handler calls it for sdma queue will crash. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Jonathan Kim <jonathan.kim@amd.com> Tested-by: Jonathan Kim <jonathan.kim@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-07drm/amdkfd: Increase SMI event fifo sizePhilip Yang
SMI event fifo size 1KB was enough to report GPU vm fault or reset event, but could drop the more frequent SVM migration events. Increase kfifo size to 8KB to store about 100 migrate events, less chance to drop the migrate events if lots of migration happened in the short period of time. Add KFD prefix to the macro name. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: James Zhu <James.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-07drm/amdkfd: Output migrate end event if migrate failedPhilip Yang
If page migration failed, also output migrate end event to match with migrate start event, with failure error_code added to the end of the migrate message macro. This will not break uAPI because application uses old message macro sscanf drop and ignore the error_code. Output GPU page fault restore end event if migration failed. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: James Zhu <James.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-10-07drm/amdkfd: Fix an eviction fence leakLang Yu
Only creating a new reference for each process instead of each VM. Fixes: 9a1c1339abf9 ("drm/amdkfd: Run restore_workers on freezable WQs") Suggested-by: Felix Kuehling <felix.kuehling@amd.com> 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>
2024-10-01drm/amdkfd: Remove an unused parameter in queue creationLang Yu
struct file *f is unused in queue creation, remove it. 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>
2024-09-25drm/amdkfd: Add SDMA queue quantum support for GFX12Sreekant Somasekharan
program SDMAx_QUEUEx_SCHEDULE_CNTL for context switch due to quantum in KFD for GFX12. Signed-off-by: Sreekant Somasekharan <sreekant.somasekharan@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Cc: stable@vger.kernel.org # 6.11.x
2024-09-25drm/amdkfd: Fix CU occupancy for GFX 9.4.3Mukul Joshi
Make CU occupancy calculations work on GFX 9.4.3 by updating the logic to handle multiple XCCs correctly. 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>
2024-09-25drm/amdkfd: Update logic for CU occupancy calculationsMukul Joshi
Currently, the code uses the IH_VMID_X_LUT register to map a queue's vmid to the corresponding PASID. This logic is racy since CP can update the VMID-PASID mapping anytime especially when there are more processes than number of vmids. Update the logic to calculate CU occupancy by matching doorbell offset of the queue with valid wave counts against the process's queues. 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>
2024-09-17drm/amdkfd: clean up code for interrupt v10Jesse Zhang
Variable hub_inst is unused. Fixes: e28604d8337e ("drm/amdkfd: Drop poison hanlding from gfx v10") 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>
2024-09-17drm/amdkfd: Move queue fs deletion after destroy checkKent Russell
We were removing the kernfs entry for queue info before checking if the queue could be destroyed. If it failed to get destroyed (e.g. during some GPU resets), then we would try to delete it later during pqm teardown, but the file was already removed. This led to a kernel WARN trying to remove size, gpuid and type. Move the remove to after the destroy check. Signed-off-by: Kent Russell <kent.russell@amd.com> Reviewed-by: Jonathan Kim <jonathan.kim@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-09-10drm/amdkfd: CRIU fixesAl Viro
Instead of trying to use close_fd() on failure exits, just have criu_get_prime_handle() store the file reference without inserting it into descriptor table. Then, once the callers are past the last failure exit, they can go and either insert all those file references into the corresponding slots of descriptor table, or drop all those file references and free the unused descriptors. Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-09-10drm/amdkfd: Fix resource leak in criu restore queueJesse Zhang
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>
2024-09-06drm/amdkfd: Document and define SVM events message macroPhilip Yang
Document how to use SMI system management interface to enable and receive SVM events. Document SVM event triggers. Define SVM events message string format macro that could be used by user mode for sscanf to parse the event. Add it to uAPI header file to make it obvious that is changing uAPI in future. No functional changes. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: James Zhu <James.Zhu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-09-06drm/amdkfd: Select reset method for poison handlingHawking Zhang
Driver mode-2 is only supported by relative new smc firmware. Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-09-06drm/amdkfd: fix missed queue reset on queue destroyJonathan Kim
If a queue is being destroyed but causes a HWS hang on removal, the KFD may issue an unnecessary gpu reset if the destroyed queue can be fixed by a queue reset. This is because the queue has been removed from the KFD's queue list prior to the preemption action on destroy so the reset call will fail to match the HQD PQ reset information against the KFD's queue record to do the actual reset. To fix this, deactivate the queue prior to preemption since it's being destroyed anyways and remove the queue from the KFD's queue list after preemption. Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-09-06drm/amdgpu: Surface svm_default_granularity, a RW module parameterRamesh Errabolu
Enables users to update SVM's default granularity, used in buffer migration and handling of recoverable page faults. Param value is set in terms of log(numPages(buffer)), e.g. 9 for a 2 MIB buffer Signed-off-by: Ramesh Errabolu <Ramesh.Errabolu@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-09-06drm/amdkfd: Add cache line size infoDavid Belanger
Populate cache line size info in topology based on information from IP discovery table. Signed-off-by: David Belanger <david.belanger@amd.com> Reviewed-by: Sreekant Somasekharan <Sreekant.Somasekharan@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-29drm/amdkfd: Don't drain ih1 for APUYifan Zhang
ih1 is not initialized for APUs. Don't drain it or NULL pointer error will be triggered. Fixes: 6ef29715ac06 ("drm/amdkfd: Change kfd/svm page fault drain handling") Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-23drm/amdkfd: Change kfd/svm page fault drain handlingXiaogang Chen
When app unmap vm ranges(munmap) kfd/svm starts drain pending page fault and not handle any incoming pages fault of this process until a deferred work item got executed by default system wq. The time period of "not handle page fault" can be long and is unpredicable. That is advese to kfd performance on page faults recovery. This patch uses time stamp of incoming page fault to decide to drop or recover page fault. When app unmap vm ranges kfd records each gpu device's ih ring current time stamp. These time stamps are used at kfd page fault recovery routine. Any page fault happened on unmapped ranges after unmap events is application bug that accesses vm range after unmap. It is not driver work to cover that. By using time stamp of page fault do not need drain page faults at deferred work. So, the time period that kfd does not handle page faults is reduced and can be controlled. Signed-off-by: Xiaogang.Chen <Xiaogang.Chen@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-23drm/amdgpu/gfx12: set UNORD_DISPATCH in compute MQDsAlex Deucher
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. Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3575 Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-23drm/amdkfd: Drop poison hanlding from gfx v10Hawking Zhang
Not supported. Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-23drm/amdkfd: Check int source id for utcl2 poison eventHawking Zhang
Traditional utcl2 fault_status polling does not work in SRIOV environment. The polling of fault status register from guest side will be dropped by hardware. Driver should switch to check utcl2 interrupt source id to identify utcl2 poison event. It is set to 1 when poisoned data interrupts are signaled. v2: drop the unused local variable (Tao) Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Tao Zhou <tao.zhou1@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-20drm/amdkfd: Update BadOpcode Interrupt handling with MESMukul Joshi
Based on the recommendation of MEC FW, update BadOpcode interrupt handling by unmapping all queues, removing the queue that got the interrupt from scheduling and remapping rest of the queues back when using MES scheduler. This is done to prevent the case where unmapping of the bad queue can fail thereby causing a GPU reset. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Acked-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-20drm/amdkfd: Update queue unmap after VM fault with MESMukul Joshi
MEC FW expects MES to unmap all queues when a VM fault is observed on a queue and then resumed once the affected process is terminated. Use the MES Suspend and Resume APIs to achieve this. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Acked-by: Alex Deucher <alexander.deucher@amd.com> Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-08-20drm/amdkfd: Enable processes isolation on gfx9Amber Lin
When amdgpu enable enforce_isolation, KFD enables single-process mode in HWS and sets exec_cleaner_shader bit in MAP_PROCESS. Signed-off-by: Amber Lin <Amber.Lin@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
generated by cgit v1.2.3 (git 2.39.1) at 2025-07-31 18:48:26 +0000