kernel/drivers/gpu/drm/amd/amdkfd/kfd_priv.h, branch linux-rolling-stable

amd/amdkfd: enhance kfd process check in switch partition

2025-11-13T20:37:32Z

[ Upstream commit 45da20e00d5da842e17dfc633072b127504f0d0e ] 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 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 Reviewed-by: Philip.Yang Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: Tie UNMAP_LATENCY to queue_preemption

2025-11-13T20:37:07Z

[ Upstream commit f3820e9d356132e18405cd7606e22dc87ccfa6d1 ] When KFD asks CP to preempt queues, other than preempt CP queues, CP also requests SDMA to preempt SDMA queues with UNMAP_LATENCY timeout. Currently queue_preemption_timeout_ms is 9000 ms by default but can be configured via module parameter. KFD_UNMAP_LATENCY_MS is hard coded as 4000 ms though. This patch ties KFD_UNMAP_LATENCY_MS to queue_preemption_timeout_ms so in a slow system such as emulator, both CP and SDMA slowness are taken into account. Signed-off-by: Amber Lin Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher Signed-off-by: Sasha Levin

drm/amdkfd: allow compute partition mode switch with cgroup exclusions

2025-06-18T16:19:17Z

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 Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher

amd/amdkfd: Trigger segfault for early userptr unmmapping

2025-05-07T21:45:09Z

If applications unmap the memory before destroying the userptr, it needs trigger a segfault to notify user space to correct the free sequence in VM debug mode. v2: Send gpu access fault to user space v3: Report gpu address to user space, remove unnecessary params v4: update pr_err into one line, remove userptr log info Signed-off-by: Shane Xiao Acked-by: Christian König Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher

drm/amdkfd: add pasid debugfs entries

2025-04-30T22:06:14Z

the entries will be appearing at /sys/kernel/debug/kfd/proc//pasid_. Signed-off-by: Eric Huang Reviewed-by: Harish Kasiviswanathan Signed-off-by: Alex Deucher

drm/amdkfd: Add pm_config_dequeue_wait_counts API

2025-03-10T17:23:12Z

Update pm_update_grace_period() to more cleaner pm_config_dequeue_wait_counts(). Previously, grace_period variable was overloaded as a variable and a macro, making it inflexible to configure additional dequeue wait times. pm_config_dequeue_wait_counts() now takes in a cmd / variable. This allows flexibility to update different dequeue wait times. Signed-off-by: Harish Kasiviswanathan Reviewed-by: Jonathan Kim Signed-off-by: Alex Deucher

drm/amdkfd: remove unused debug gws support status variable

2025-03-07T17:53:13Z

Remove unused declaration of gws_debug_workaround. Signed-off-by: Jonathan Kim Reviewed-by: Amber Lin Signed-off-by: Alex Deucher

drm/amdgpu: Remove unused pqm_get_kernel_queue

2025-03-05T15:44:51Z

pqm_get_kernel_queue() has been unused since 2022's commit 5bdd3eb25354 ("drm/amdkfd: Remove unused old debugger implementation") Remove it. Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Alex Deucher

drm/amdkfd: Remove unused functions

2025-02-13T02:02:56Z

kfd_device_by_pci_dev(), kfd_get_pasid_limit() and kfd_set_pasid_limit() have been unused since 2023's commit c99a2e7ae291 ("drm/amdkfd: drop IOMMUv2 support") Remove them. Signed-off-by: Dr. David Alan Gilbert Signed-off-by: Alex Deucher

drm/amdkfd: Have kfd driver use same PASID values from graphic driver

2025-02-13T02:02:55Z

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 Reviewed-by: Felix Kuehling Signed-off-by: Alex Deucher