On 9/24/2025 10:29 AM, Yifan Zhang wrote:
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 <[email protected]>
---
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 9 +++++++++
drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 2 ++
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 4 ++++
3 files changed, 15 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 051a00152b08..488c8c0e6ccd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -1493,6 +1493,15 @@ int kgd2kfd_check_and_lock_kfd(struct kfd_dev *kfd)
mutex_lock(&kfd_processes_mutex);
+ /* kfd_processes_count is per kfd_dev, return -EBUSY without
+ * further check
+ */
+ if (!!atomic_read(&kfd->kfd_processes_count)) {
+ pr_debug("process_wq_release not finished\n");
+ r = -EBUSY;
+ goto out;
+ }
+
if (hash_empty(kfd_processes_table) && !kfd_is_locked(kfd))
goto out;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d01ef5ac0766..70ef051511bb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -382,6 +382,8 @@ struct kfd_dev {
/* for dynamic partitioning */
int kfd_dev_lock;
+
+ atomic_t kfd_processes_count;
Why need add kfd process count per kfd_dev? A kfd process uses all kfd
nodes on system. Is there a case that a kfd process just use some kfd_dev?
It does not seems the root cause or the solution.
Regards
Xiaogang
};
enum kfd_mempool {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 5be28c6c4f6a..ddfe30c13e9d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -1088,6 +1088,8 @@ static void kfd_process_destroy_pdds(struct kfd_process
*p)
pdd->runtime_inuse = false;
}
+ atomic_dec(&pdd->dev->kfd->kfd_processes_count);
+
kfree(pdd);
p->pdds[i] = NULL;
}
@@ -1649,6 +1651,8 @@ struct kfd_process_device
*kfd_create_process_device_data(struct kfd_node *dev,
/* Init idr used for memory handle translation */
idr_init(&pdd->alloc_idr);
+ atomic_inc(&dev->kfd->kfd_processes_count);
+
return pdd;
}
