aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/gpu/drm/amd/amdkfd/kfd_process.c (follow)
AgeCommit message (Collapse)AuthorFilesLines
2025-09-25amd/amdkfd: enhance kfd process check in switch partitionYifan Zhang1-0/+4
current switch partition only check if kfd_processes_table is empty. kfd_prcesses_table entry is deleted in kfd_process_notifier_release, but kfd_process tear down is in kfd_process_wq_release. consider two processes: Process A (workqueue) -> kfd_process_wq_release -> Access kfd_node member Process B switch partition -> amdgpu_xcp_pre_partition_switch -> amdgpu_amdkfd_device_fini_sw -> kfd_node tear down. Process A and B may trigger a race as shown in dmesg log. This patch is to resolve the race by adding an atomic kfd_process counter kfd_processes_count, it increment as create kfd process, decrement as finish kfd_process_wq_release. v2: Put kfd_processes_count per kfd_dev, move decrement to kfd_process_destroy_pdds and bug fix. (Philip Yang) [3966658.307702] divide error: 0000 [#1] SMP NOPTI [3966658.350818] i10nm_edac [3966658.356318] CPU: 124 PID: 38435 Comm: kworker/124:0 Kdump: loaded Tainted [3966658.356890] Workqueue: kfd_process_wq kfd_process_wq_release [amdgpu] [3966658.362839] nfit [3966658.366457] RIP: 0010:kfd_get_num_sdma_engines+0x17/0x40 [amdgpu] [3966658.366460] Code: 00 00 e9 ac 81 02 00 66 66 2e 0f 1f 84 00 00 00 00 00 90 0f 1f 44 00 00 48 8b 4f 08 48 8b b7 00 01 00 00 8b 81 58 26 03 00 99 <f7> be b8 01 00 00 80 b9 70 2e 00 00 00 74 0b 83 f8 02 ba 02 00 00 [3966658.380967] x86_pkg_temp_thermal [3966658.391529] RSP: 0018:ffffc900a0edfdd8 EFLAGS: 00010246 [3966658.391531] RAX: 0000000000000008 RBX: ffff8974e593b800 RCX: ffff888645900000 [3966658.391531] RDX: 0000000000000000 RSI: ffff888129154400 RDI: ffff888129151c00 [3966658.391532] RBP: ffff8883ad79d400 R08: 0000000000000000 R09: ffff8890d2750af4 [3966658.391532] R10: 0000000000000018 R11: 0000000000000018 R12: 0000000000000000 [3966658.391533] R13: ffff8883ad79d400 R14: ffffe87ff662ba00 R15: ffff8974e593b800 [3966658.391533] FS: 0000000000000000(0000) GS:ffff88fe7f600000(0000) knlGS:0000000000000000 [3966658.391534] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [3966658.391534] CR2: 0000000000d71000 CR3: 000000dd0e970004 CR4: 0000000002770ee0 [3966658.391535] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [3966658.391535] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400 [3966658.391536] PKRU: 55555554 [3966658.391536] Call Trace: [3966658.391674] deallocate_sdma_queue+0x38/0xa0 [amdgpu] [3966658.391762] process_termination_cpsch+0x1ed/0x480 [amdgpu] [3966658.399754] intel_powerclamp [3966658.402831] kfd_process_dequeue_from_all_devices+0x5b/0xc0 [amdgpu] [3966658.402908] kfd_process_wq_release+0x1a/0x1a0 [amdgpu] [3966658.410516] coretemp [3966658.434016] process_one_work+0x1ad/0x380 [3966658.434021] worker_thread+0x49/0x310 [3966658.438963] kvm_intel [3966658.446041] ? process_one_work+0x380/0x380 [3966658.446045] kthread+0x118/0x140 [3966658.446047] ? __kthread_bind_mask+0x60/0x60 [3966658.446050] ret_from_fork+0x1f/0x30 [3966658.446053] Modules linked in: kpatch_20765354(OEK) [3966658.455310] kvm [3966658.464534] mptcp_diag xsk_diag raw_diag unix_diag af_packet_diag netlink_diag udp_diag act_pedit act_mirred act_vlan cls_flower kpatch_21951273(OEK) kpatch_18424469(OEK) kpatch_19749756(OEK) [3966658.473462] idxd_mdev [3966658.482306] kpatch_17971294(OEK) sch_ingress xt_conntrack amdgpu(OE) amdxcp(OE) amddrm_buddy(OE) amd_sched(OE) amdttm(OE) amdkcl(OE) intel_ifs iptable_mangle tcm_loop target_core_pscsi tcp_diag target_core_file inet_diag target_core_iblock target_core_user target_core_mod coldpgs kpatch_18383292(OEK) ip6table_nat ip6table_filter ip6_tables ip_set_hash_ipportip ip_set_hash_ipportnet ip_set_hash_ipport ip_set_bitmap_port xt_comment iptable_nat nf_nat iptable_filter ip_tables ip_set ip_vs_sh ip_vs_wrr ip_vs_rr ip_vs nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 sn_core_odd(OE) i40e overlay binfmt_misc tun bonding(OE) aisqos(OE) aisqos_hotfixes(OE) rfkill uio_pci_generic uio cuse fuse nf_tables nfnetlink intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common i10nm_edac nfit x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm idxd_mdev [3966658.491237] vfio_pci [3966658.501196] vfio_pci vfio_virqfd mdev vfio_iommu_type1 vfio iax_crypto intel_pmt_telemetry iTCO_wdt intel_pmt_class iTCO_vendor_support irqbypass crct10dif_pclmul crc32_pclmul ghash_clmulni_intel rapl intel_cstate snd_hda_intel snd_intel_dspcfg snd_hda_codec snd_hda_core snd_hwdep snd_seq [3966658.508537] vfio_virqfd [3966658.517569] snd_seq_device ipmi_ssif isst_if_mbox_pci isst_if_mmio pcspkr snd_pcm idxd intel_uncore ses isst_if_common intel_vsec idxd_bus enclosure snd_timer mei_me snd i2c_i801 i2c_smbus mei i2c_ismt soundcore joydev acpi_ipmi ipmi_si ipmi_devintf ipmi_msghandler acpi_power_meter acpi_pad vfat fat [3966658.526851] mdev [3966658.536096] nfsd auth_rpcgss nfs_acl lockd grace slb_vtoa(OE) sunrpc dm_mod hookers mlx5_ib(OE) ast i2c_algo_bit drm_vram_helper drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm_ttm_helper ttm mlx5_core(OE) mlxfw(OE) [3966658.540381] vfio_iommu_type1 [3966658.544341] nvme mpt3sas tls drm nvme_core pci_hyperv_intf raid_class psample libcrc32c crc32c_intel mlxdevm(OE) i2c_core [3966658.551254] vfio [3966658.558742] scsi_transport_sas wmi pinctrl_emmitsburg sd_mod t10_pi sg ahci libahci libata rdma_ucm(OE) ib_uverbs(OE) rdma_cm(OE) iw_cm(OE) ib_cm(OE) ib_umad(OE) ib_core(OE) ib_ucm(OE) mlx_compat(OE) [3966658.563004] iax_crypto [3966658.570988] [last unloaded: diagnose] [3966658.571027] ---[ end trace cc9dbb180f9ae537 ]--- Signed-off-by: Yifan Zhang <yifan1.zhang@amd.com> Reviewed-by: Philip.Yang<Philip.Yang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2025-06-18drm/amdkfd: allow compute partition mode switch with cgroup exclusionsJonathan Kim1-1/+1
The KFD currently bars a compute partition mode switch while a KFD process exists. Since cgroup excluded devices remain excluded for the lifetime of a KFD process and user space is able to mode switch single devices, allow users to mode switch a device with any running process that has been cgroup excluded from this device. 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>
2025-04-30drm/amdkfd: add pasid debugfs entriesEric Huang1-0/+3
the entries will be appearing at /sys/kernel/debug/kfd/proc/<pid>/pasid_<gpuid>. 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>
2025-04-11drm/amdkfd: add smi events for process start and endEric Huang1-0/+4
rocm-smi will be able to show the events for KFD process start/end, it is the implementation of this feature. Signed-off-by: Eric Huang <jinhuieric.huang@amd.com> Reviewed-by: Kent Russell <kent.russell@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2025-02-27drm/amdkfd: Fix mode1 reset crash issuePhilip Yang1-0/+17
If HW scheduler hangs and mode1 reset is used to recover GPU, KFD signal user space to abort the processes. After process abort exit, user queues still use the GPU to access system memory before h/w is reset while KFD cleanup worker free system memory and free VRAM. There is use-after-free race bug that KFD allocate and reuse the freed system memory, and user queue write to the same system memory to corrupt the data structure and cause driver crash. To fix this race, KFD cleanup worker terminate user queues, then flush reset_domain wq to wait for any GPU ongoing reset complete, and then free outstanding BOs. Signed-off-by: Philip Yang <Philip.Yang@amd.com> Reviewed-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2025-02-27drm/amdkfd: KFD release_work possible circular lockingPhilip Yang1-8/+8
If waiting for gpu reset done in KFD release_work, thers is WARNING: possible circular locking dependency detected #2 kfd_create_process kfd_process_mutex flush kfd release work #1 kfd release work wait for amdgpu reset work #0 amdgpu_device_gpu_reset kgd2kfd_pre_reset kfd_process_mutex Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock((work_completion)(&p->release_work)); lock((wq_completion)kfd_process_wq); lock((work_completion)(&p->release_work)); lock((wq_completion)amdgpu-reset-dev); To fix this, KFD create process move flush release work outside kfd_process_mutex. 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>
2025-02-19drm/amdkfd: Fix error handling for missing PASID in 'kfd_process_device_init_vm'Srinivasan Shanmugam1-0/+1
In the kfd_process_device_init_vm function, a valid error code is now returned when the associated Process Address Space ID (PASID) is not present. If the address space virtual memory (avm) does not have an associated PASID, the function sets the ret variable to -EINVAL before proceeding to the error handling section. This ensures that the calling function, such as kfd_ioctl_acquire_vm, can appropriately handle the error, thereby preventing any issues during virtual memory initialization. Fixes the below: drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_process.c:1694 kfd_process_device_init_vm() warn: missing error code 'ret' drivers/gpu/drm/amd/amdgpu/../amdkfd/kfd_process.c 1647 int kfd_process_device_init_vm(struct kfd_process_device *pdd, 1648 struct file *drm_file) 1649 { ... 1690 1691 if (unlikely(!avm->pasid)) { 1692 dev_warn(pdd->dev->adev->dev, "WARN: vm %p has no pasid associated", 1693 avm); --> 1694 goto err_get_pasid; ret = -EINVAL? 1695 } Fixes: 8544374c0f82 ("drm/amdkfd: Have kfd driver use same PASID values from graphic driver") Reported by: Dan Carpenter <dan.carpenter@linaro.org> Cc: Xiaogang Chen <xiaogang.chen@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>
2025-02-12drm/amdkfd: Fix pasid value leakXiaogang Chen1-4/+1
Curret kfd does not allocate pasid values, instead uses pasid value for each vm from graphic driver. So should not prevent graphic driver from releasing pasid values since the values are allocated by graphic driver, not kfd driver anymore. This patch does not stop graphic driver release pasid values. Fixes: 8544374c0f82 ("drm/amdkfd: Have kfd driver use same PASID values from graphic driver") 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>
2025-02-12drm/amdkfd: Have kfd driver use same PASID values from graphic driverXiaogang Chen1-49/+66
Current kfd driver has its own PASID value for a kfd process and uses it to locate vm at interrupt handler or mapping between kfd process and vm. That design is not working when a physical gpu device has multiple spatial partitions, ex: adev in CPX mode. This patch has kfd driver use same pasid values that graphic driver generated which is per vm per pasid. These pasid values are passed to fw/hardware. We do not need change interrupt handler though more pasid values are used. Also, pasid values at log are replaced by user process pid; pasid values are not exposed to user. Users see their process pids that have meaning in user space. 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>
2025-01-06drm/amdkfd: wq_release signals dma_fence only when availableZhu Lingshan1-1/+2
kfd_process_wq_release() signals eviction fence by dma_fence_signal() which wanrs if dma_fence is NULL. kfd_process->ef is initialized by kfd_process_device_init_vm() through ioctl. That means the fence is NULL for a new created kfd_process, and close a kfd_process right after open it will trigger the warning. This commit conditionally signals the eviction fence in kfd_process_wq_release() only when it is available. [ 503.660882] WARNING: CPU: 0 PID: 9 at drivers/dma-buf/dma-fence.c:467 dma_fence_signal+0x74/0xa0 [ 503.782940] Workqueue: kfd_process_wq kfd_process_wq_release [amdgpu] [ 503.789640] RIP: 0010:dma_fence_signal+0x74/0xa0 [ 503.877620] Call Trace: [ 503.880066] <TASK> [ 503.882168] ? __warn+0xcd/0x260 [ 503.885407] ? dma_fence_signal+0x74/0xa0 [ 503.889416] ? report_bug+0x288/0x2d0 [ 503.893089] ? handle_bug+0x53/0xa0 [ 503.896587] ? exc_invalid_op+0x14/0x50 [ 503.900424] ? asm_exc_invalid_op+0x16/0x20 [ 503.904616] ? dma_fence_signal+0x74/0xa0 [ 503.908626] kfd_process_wq_release+0x6b/0x370 [amdgpu] [ 503.914081] process_one_work+0x654/0x10a0 [ 503.918186] worker_thread+0x6c3/0xe70 [ 503.921943] ? srso_alias_return_thunk+0x5/0xfbef5 [ 503.926735] ? srso_alias_return_thunk+0x5/0xfbef5 [ 503.931527] ? __kthread_parkme+0x82/0x140 [ 503.935631] ? __pfx_worker_thread+0x10/0x10 [ 503.939904] kthread+0x2a8/0x380 [ 503.943132] ? __pfx_kthread+0x10/0x10 [ 503.946882] ret_from_fork+0x2d/0x70 [ 503.950458] ? __pfx_kthread+0x10/0x10 [ 503.954210] ret_from_fork_asm+0x1a/0x30 [ 503.958142] </TASK> [ 503.960328] ---[ end trace 0000000000000000 ]--- Fixes: 967d226eaae8 ("dma-buf: add WARN_ON() illegal dma-fence signaling") Signed-off-by: Zhu Lingshan <lingshan.zhu@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-12-10drm/amdkfd: add gc 9.5.0 support on kfdAlex Sierra1-2/+3
Initial support for GC 9.5.0. v2: squash in pqm_clean_queue_resource() fix from Lijo Signed-off-by: Alex Sierra <alex.sierra@amd.com> Reviewed-by: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-12-10drm/amdkfd: pause autosuspend when creating pddJesse.zhang@amd.com1-21/+2
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
2024-11-11drm/amdkfd: change kfd process kref count at creationXiaogang Chen1-8/+6
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 Can1-2/+3
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>
2024-11-04drm/amdkfd: Use dynamic allocation for CU occupancy array in ↵Srinivasan Shanmugam1-3/+6
'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>
2024-10-15drm/amdkfd: Accounting pdd vram_usage for svmPhilip Yang1-2/+2
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: Fix an eviction fence leakLang Yu1-2/+5
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>
2024-09-25drm/amdkfd: Fix CU occupancy for GFX 9.4.3Mukul Joshi1-3/+17
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 Joshi1-1/+13
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>
2024-08-06drm/amdkfd: support per-queue reset on gfx9Jonathan Kim1-0/+2
Support per-queue reset for GFX9. The recommendation is for the driver to target reset the HW queue via a SPI MMIO register write. Since this requires pipe and HW queue info and MEC FW is limited to doorbell reports of hung queues after an unmap failure, scan the HW queue slots defined by SET_RESOURCES first to identify the user queue candidates to reset. Only signal reset events to processes that have had a queue reset. If queue reset fails, fall back to GPU reset. 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>
2024-07-23drm/amdkfd: amdkfd_free_gtt_mem clear the correct pointerPhilip Yang1-1/+1
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>
2024-07-01drm/amdkfd: Use device based logging for errorsLijo Lazar1-9/+15
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>
2024-05-02drm/amdgpu: Add gfx v9_4_4 ip blockHawking Zhang1-1/+2
Add gfx v9_4_4 ip block support Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Reviewed-by: Le Ma <le.ma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-04-30drm/amdkfd: Flush the process wq before creating a kfd_processLancelot SIX1-0/+8
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>
2024-04-26drm/amdkfd: Fix rescheduling of restore workerFelix Kuehling1-3/+3
Handle the case that the restore worker was already scheduled by another eviction while the restore was in progress. Fixes: 9a1c1339abf9 ("drm/amdkfd: Run restore_workers on freezable WQs") Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Tested-by: Yunxiang Li <Yunxiang.Li@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-04-18drm/amdkfd: Fix eviction fence handlingFelix Kuehling1-4/+5
Handle case that dma_fence_get_rcu_safe returns NULL. If restore work is already scheduled, only update its timer. The same work item cannot be queued twice, so undo the extra queue eviction. Fixes: 9a1c1339abf9 ("drm/amdkfd: Run restore_workers on freezable WQs") Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Philip Yang <Philip.Yang@amd.com> Tested-by: Gang BA <Gang.Ba@amd.com> Reviewed-by: Gang BA <Gang.Ba@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2024-04-12drm/amdkfd: Fix memory leak in create_process failureFelix Kuehling1-2/+2
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>
2024-01-09drm/amdkfd: Fix sparse __rcu annotation warningsFelix Kuehling1-2/+5
Properly mark kfd_process->ef as __rcu and consistently use the right accessor functions. Reported-by: kernel test robot <lkp@intel.com> Closes: https://lore.kernel.org/oe-kbuild-all/202312052245.yFpBSgNH-lkp@intel.com/ Signed-off-by: Felix Kuehling <felix.kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-11-29drm/amdkfd: Run restore_workers on freezable WQsFelix Kuehling1-34/+53
Make restore workers freezable so we don't have to explicitly flush them in suspend and GPU reset code paths, and we don't accidentally try to restore BOs while the GPU is suspended. Not having to flush restore_work also helps avoid lock/fence dependencies in the GPU reset case where we're not allowed to wait for fences. A side effect of this is, that we can now have multiple concurrent threads trying to signal the same eviction fence. Rework eviction fence signaling and replacement to account for that. The GPU reset path can no longer rely on restore_process_worker to resume queues because evict/restore workers can run independently of it. Instead call a new restore_process_helper directly. This is an RFC and request for testing. v2: - Reworked eviction fence signaling - Introduced restore_process_helper v3: - Handle unsignaled eviction fences in restore_process_bos Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Tested-by: Emily Deng <Emily.Deng@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-11-17drm/amdkfd: Move TLB flushing logic into amdgpuFelix Kuehling1-31/+0
This will make it possible for amdgpu GEM ioctls to flush TLBs on compute VMs. This removes VMID-based TLB flushing and always uses PASID-based flushing. This still works because it scans the VMID-PASID mapping registers to find the right VMID. It's only slightly less efficient. This is not a production use case. Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Christian König <christian.koenig@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-11-07drm/amd: Disable XNACK on SRIOV environmentSurbhi Kakarya1-1/+6
The purpose of this patch is to disable XNACK or set XNACK OFF mode on SRIOV platform which doesn't support it. This will prevent user-space application to fail or result into unexpected behaviour whenever the application need to run test-case in XNACK ON mode. Signed-off-by: Surbhi Kakarya <surbhi.kakarya@amd.com> Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-08-11drm/amdkfd: drop IOMMUv2 supportAlex Deucher1-16/+0
Now that we use the dGPU path for all APUs, drop the IOMMUv2 support. v2: drop the now unused queue manager functions for gfx7/8 APUs Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Tested-by: Mike Lothian <mike@fireburn.co.uk> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-08-07drm/amdgpu: use doorbell mgr for kfd process doorbellsShashank Sharma1-39/+1
This patch: - adds a doorbell object in kfd pdd structure. - allocates doorbells for a process while creating its queue. - frees the doorbells with pdd destroy. - moves doorbell bitmap init function to kfd_doorbell.c PS: This patch ensures that we don't break the existing KFD functionality, but now KFD userspace library should also create doorbell pages as AMDGPU GEM objects using libdrm functions in userspace. The reference code for the same is available with AMDGPU Usermode queue libdrm MR. Once this is done, we will not need to create process doorbells in kernel. V2: - Do not use doorbell wrapper API, use amdgpu_bo_create_kernel instead (Alex). - Do not use custom doorbell structure, instead use separate variables for bo and doorbell_bitmap (Alex) V3: - Do not allocate doorbell page with PDD, delay doorbell process page allocation until really needed (Felix) Cc: Alex Deucher <alexander.deucher@amd.com> Cc: Christian Koenig <christian.koenig@amd.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Acked-by: Christian König <christian.koenig@amd.com> Reviewed-by: Felix Kuehling <Felilx.Kuehling@amd.com> Signed-off-by: Shashank Sharma <shashank.sharma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-30drm/amdkfd: Update interrupt handling for GFX 9.4.3Mukul Joshi1-0/+9
For GFX 9.4.3, interrupt handling needs to be updated for: - Interrupt cookie will have a NodeId field. Each KFD node needs to check the NodeId before processing the interrupt. - For CPX mode, there are additional checks of client ID needed to process the interrupt. - Add NodeId to the process drain interrupt. 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>
2023-06-09drm/amdkfd: update process interrupt handling for debug eventsJonathan Kim1-0/+47
The debugger must be notified by any debugger subscribed exception that comes from hardware interrupts. If a debugger session exits, any exceptions it subscribed to may still have interrupts in the interrupt ring buffer or KGD/KFD pipeline. To prevent a new session from inheriting stale interrupts, when a new queue is created, open an interrupt drain and allow the IH ring to drain from a timestamped checkpoint. Then inject a custom IV so that once the custom IV is picked up by the KFD, it's safe to close the drain and proceed with queue creation. The drain must also be on debug disable as SW interrupts may still be processed. Drain at this time and clear all the exception status. The debugger may also not be attached nor subscibed to certain exceptions so forward them directly to the runtime. GFX10 also requires its own IV processing, hence the creation of kfd_int_process_v10.c. This is because the IV from SQ interrupts are packed into a new continguous format unlike GFX9. To make this clear, a separate interrupting handling code file was created. 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>
2023-06-09drm/amdkfd: add debug trap enabled flag to tmaJay Cornwall1-0/+15
Trap handler behavior will differ when a debugger is attached. Make the debug trap flag available in the trap handler TMA. Update it when the debug trap ioctl is invoked. Signed-off-by: Jay Cornwall <jay.cornwall@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Jonathan Kim <jonathan.kim@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: add send exception operationJonathan Kim1-1/+70
Add a debug operation that allows the debugger to send an exception directly to runtime through a payload address. For memory violations, normal vmfault signals will be applied to notify runtime instead after passing in the saved exception data when a memory violation was raised to the debugger. For runtime exceptions, this will unblock the runtime enable function which will be explained and implemented in a follow up patch. 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>
2023-06-09drm/amdkfd: add raise exception event functionJonathan Kim1-0/+2
Exception events can be generated from interrupts or queue activitity. The raise event function will save exception status of a queue, device or process then notify the debugger of the status change by writing to a debugger polled file descriptor that the debugger provides during debug attach. For memory violation exceptions, extra exception data will be saved. The debugger will be able to query the saved exception states by query operation that will be provided by follow up patches. 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>
2023-06-09drm/amdkfd: add per process hw trap enable and disable functionsJonathan Kim1-0/+10
To enable HW debug mode per process, all devices must be debug enabled successfully. If a failure occures, rewind the enablement of debug mode on the enabled devices. A power management scenario that needs to be considered is HW debug mode setting during GFXOFF. During GFXOFF, these registers will be unreachable so we have to transiently disable GFXOFF when setting. Also, some devices don't support the RLC save restore function for these debug registers so we have to disable GFXOFF completely during a debug session. Cooperative launch also has debugging restriction based on HW/FW bugs. If such bugs exists, the debugger cannot attach to a process that uses GWS resources nor can GWS resources be requested if a process is being debugged. Multi-process debug devices can only enable trap temporaries based on certain runtime scenerios, which will be explained when the runtime enable functions are implemented in a follow up patch. 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>
2023-06-09drm/amdgpu: prepare map process for multi-process debug devicesJonathan Kim1-0/+5
Unlike single process debug devices, multi-process debug devices allow debug mode setting per-VMID (non-device-global). Because the HWS manages PASID-VMID mapping, the new MAP_PROCESS API allows the KFD to forward the required SPI debug register write requests. To request a new debug mode setting change, the KFD must be able to preempt all queues then remap all queues with these new setting requests for MAP_PROCESS to take effect. Note that by default, trap enablement in non-debug mode must be disabled for performance reasons for multi-process debug devices due to setup overhead in FW. 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>
2023-06-09drm/amdkfd: fix kfd_suspend_all_processesJonathan Kim1-1/+1
Flush delayed restore work in kfd_suspend_all_queues instead of cancelling. Cancelling the work before it runs results in the queues becoming permanently disabled. Flushing the work ensures that the queue suspend/resume state stays balanced. 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>
2023-06-09drm/amdkfd: prepare per-process debug enable and disableJonathan Kim1-20/+40
The ROCm debugger will attach to a process to debug by PTRACE and will expect the KFD to prepare a process for the target PID, whether the target PID has opened the KFD device or not. This patch is to explicity handle this requirement. Further HW mode setting and runtime coordination requirements will be handled in following patches. In the case where the target process has not opened the KFD device, a new KFD process must be created for the target PID. The debugger as well as the target process for this case will have not acquired any VMs so handle process restoration to correctly account for this. To coordinate with HSA runtime, the debugger must be aware of the target process' runtime enablement status and will copy the runtime status information into the debugged KFD process for later query. On enablement, the debugger will subscribe to a set of exceptions where each exception events will notify the debugger through a pollable FIFO file descriptor that the debugger provides to the KFD to manage. Finally on process termination of either the debugger or the target, debugging must be disabled if it has not been done so. 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>
2023-06-09drm/amdkfd: Use xcc mask for identifying xccLijo Lazar1-4/+4
Instead of start xcc id and number of xcc per node, use the xcc mask which is the mask of logical ids of xccs belonging to a parition. Signed-off-by: Lijo Lazar <lijo.lazar@amd.com> Reviewed-by: Le Ma <le.ma@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: Update SMI events for GFX9.4.3Mukul Joshi1-3/+3
On GFX 9.4.3, there can be multiple KFD nodes. As a result, SMI events for SVM, queue evict/restore should be raised for each node independently. 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>
2023-06-09drm/amdkfd: pass kfd_node ref to svm migration apiAlex Sierra1-3/+3
This work is required for GC 9.4.3, previous to support memory partitions per node at SVM. When multiple partition is configured, every BO should be allocated inside one specific partition which corresponds to the current amdgpu_device and kfd_node. v2: squash in compilation fix (Alex) v3: squash in fix for pre-gfx 9.4.3 (Alex) v4: squash in best_loc fix (Alex) Signed-off-by: Alex Sierra <alex.sierra@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: Rework kfd_locked handlingMukul Joshi1-1/+7
Currently, even if kfd_locked is set, a process is first created and then removed to work around a race condition in updating kfd_locked flag. Rework kfd_locked handling to ensure no processes is created if kfd_locked is set. This is achieved by updating kfd_locked under kfd_processes_mutex. With this there is no need for kfd_locked to be an atomic counter. Instead, it can be a regular integer. 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>
2023-06-09drm/amdgpu: Add XCC inst to PASID TLB flushingMukul Joshi1-2/+5
Add XCC instance to select the correct KIQ ring when flushing TLBs on a multi-XCC setup. Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: Add XCC instance to kgd2kfd interface (v3)Mukul Joshi1-1/+1
Gfx 9 starts to have multiple XCC instances in one device. Add instance parameter to kgd2kfd functions where XCC instance was hard coded as 0. Also, update code to pass the correct instance number when running on a multi-XCC setup. v2: introduce the XCC instance to gfx v11 (Morris) v3: rebase (Alex) Signed-off-by: Amber Lin <Amber.Lin@amd.com> Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-06-09drm/amdkfd: Introduce kfd_node struct (v5)Mukul Joshi1-27/+27
Introduce a new structure, kfd_node, which will now represent a compute node. kfd_node is carved out of kfd_dev structure. kfd_dev struct now will become the parent of kfd_node, and will store common resources such as doorbells, GTT sub-alloctor etc. kfd_node struct will store all resources specific to a compute node, such as device queue manager, interrupt handling etc. This is the first step in adding compute partition support in KFD. v2: introduce kfd_node struct to gc v11 (Hawking) v3: make reference to kfd_dev struct through kfd_node (Morris) v4: use kfd_node instead for kfd isr/mqd functions (Morris) v5: rebase (Alex) Signed-off-by: Mukul Joshi <mukul.joshi@amd.com> Tested-by: Amber Lin <Amber.Lin@amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> Signed-off-by: Hawking Zhang <Hawking.Zhang@amd.com> Signed-off-by: Morris Zhang <Shiwu.Zhang@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
2023-03-20Merge tag 'amd-drm-next-6.4-2023-03-17' of ↵Dave Airlie1-11/+64
https://gitlab.freedesktop.org/agd5f/linux into drm-next amd-drm-next-6.4-2023-03-17: amdgpu: - Misc code cleanups - Documentation fixes - Make kobj structures const - Add thermal throttling adjustments for supported APUs - UMC RAS fixes - Display reset fixes - DCN 3.2 fixes - Freesync fixes - DC code reorg - Generalize dmabuf import to work with KFD - DC DML fixes - SRIOV fixes - UVD code cleanups - IH 4.4.2 updates - HDP 4.4.2 updates - SDMA 4.4.2 updates - PSP 13.0.6 updates - Add capped/uncapped workload handling for supported APUs - DCN 3.1.4 updates - Re-org DC Kconfig - USB4 fixes - Reorg DC plane and stream handling - Register vga_switcheroo for apple-gmux - SMU 13.0.6 updates - Fix error checking in read_mm_registers functions for affected families - VCN 4.0.4 fix - Drop redundant pci_enable_pcie_error_reporting() call - RDNA2 SMU OD suspend/resume fix - Expose additional memory stats via fdinfo - RAS fixes - Misc display fixes - DP MST fixes - IOMMU regression fix for KFD amdkfd: - Make kobj structures const - Support for exporting buffers via dmabuf - Multi-VMA page migration fixes - NBIO fixes - Misc code cleanups - Fix possible double free - Fix possible UAF radeon: - iMac fix UAPI: - KFD dmabuf export support. Required for importing KFD buffers into GEM contexts and for RDMA P2P support. Proposed user mode changes: https://github.com/fxkamd/ROCT-Thunk-Interface/commits/fxkamd/dmabuf From: Alex Deucher <alexander.deucher@amd.com> Link: https://patchwork.freedesktop.org/patch/msgid/20230317164416.138340-1-alexander.deucher@amd.com
generated by cgit v1.2.3 (git 2.39.1) at 2025-12-25 13:28:21 +0000