The `amdgpu_enforce_isolation_wq` is allocated with the WQ_MEM_RECLAIM
flag to mitigate workqueue flushing related to memory reclamation & to
ensure proper memory handling during deferred work execution.
Fixes the below:
[ 2333.852549] workqueue: WQ_MEM_RECLAIM gfx_0.0.0:drm_sched_run_job_work [gpu_sched] is flushing !WQ_MEM_RECLAIM events:amdgpu_gfx_enforce_isolation_handler [amdgpu]
[ 2333.853008] WARNING: CPU: 10 PID: 6250 at kernel/workqueue.c:3704 check_flush_dependency+0x124/0x130
[ 2333.853020] Modules linked in: amdgpu(OE) amdxcp drm_exec gpu_sched drm_buddy drm_ttm_helper ttm drm_suballoc_helper drm_client_lib drm_display_helper cec rc_core drm_kms_helper rfcomm nf_conntrack_netlink xfrm_user xfrm_algo xt_addrtype br_netfilter xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp nft_compat nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables libcrc32c nfnetlink bridge stp llc overlay cmac algif_hash algif_skcipher af_alg bnep intel_rapl_msr amd_atl intel_rapl_common snd_hda_codec_realtek binfmt_misc snd_hda_codec_generic snd_hda_scodec_component snd_hda_codec_hdmi snd_hda_intel snd_intel_dspcfg snd_intel_sdw_acpi edac_mce_amd snd_hda_codec snd_hda_core snd_hwdep kvm_amd snd_pcm kvm iwlmvm crct10dif_pclmul snd_seq_midi polyval_clmulni nls_iso8859_1 snd_seq_midi_event mac80211 polyval_generic snd_rawmidi ghash_clmulni_intel libarc4 sha512_ssse3 joydev sha256_ssse3 snd_seq btusb sha1_ssse3 snd_seq_device aesni_intel input_leds btrtl crypto_simd cryptd
[ 2333.853178] btintel snd_timer iwlwifi rapl btbcm btmtk gigabyte_wmi mxm_wmi snd wmi_bmof k10temp bluetooth ccp cfg80211 soundcore mac_hid sch_fq_codel msr parport_pc nfsd ppdev lp parport auth_rpcgss nfs_acl drm lockd grace efi_pstore sunrpc ip_tables x_tables autofs4 hid_generic crc32_pclmul nvme i2c_piix4 usbhid i2c_smbus hid nvme_core ahci igb libahci dca i2c_algo_bit video wmi
[ 2333.853274] CPU: 10 UID: 0 PID: 6250 Comm: kworker/u48:2 Tainted: G U W OE 6.12.0-amdrelease6dot4forleftoverlocals #27
[ 2333.853282] Tainted: [U]=USER, [W]=WARN, [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
[ 2333.853286] Hardware name: Gigabyte Technology Co., Ltd. X570 AORUS PRO WIFI/X570 AORUS PRO WIFI, BIOS F36a 02/16/2022
[ 2333.853291] Workqueue: gfx_0.0.0 drm_sched_run_job_work [gpu_sched]
[ 2333.853302] RIP: 0010:check_flush_dependency+0x124/0x130
[ 2333.853307] Code: 55 18 4d 89 e0 48 8d 8b 90 01 00 00 48 c7 c7 10 98 3e 8e c6 05 9e 30 7b 02 01 48 8b 70 08 48 81 c6 90 01 00 00 e8 9c 21 fd ff <0f> 0b e9 ff fe ff ff e9 98 d9 0c 01 90 90 90 90 90 90 90 90 90 90
[ 2333.853313] RSP: 0018:ffff9fdd82c07ac0 EFLAGS: 00010086
[ 2333.853319] RAX: 0000000000000000 RBX: ffff89b840050e00 RCX: 0000000000000027
[ 2333.853323] RDX: ffff89bb6dbf1a88 RSI: 0000000000000001 RDI: ffff89bb6dbf1a80
[ 2333.853327] RBP: ffff9fdd82c07ae8 R08: 0000000000000003 R09: 0000000000000001
[ 2333.853331] R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffc1864470
[ 2333.853335] R13: ffff89b856e58d80 R14: 0000000000000000 R15: ffff89bb6d808900
[ 2333.853340] FS: 0000000000000000(0000) GS:ffff89bb6da00000(0000) knlGS:0000000000000000
[ 2333.853344] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2333.853348] CR2: 00005613aff86098 CR3: 0000000337e5c000 CR4: 0000000000350ef0
[ 2333.853353] Call Trace:
[ 2333.853358] <TASK>
[ 2333.853365] ? show_regs+0x69/0x80
[ 2333.853373] ? __warn+0x93/0x1a0
[ 2333.853382] ? check_flush_dependency+0x124/0x130
[ 2333.853389] ? report_bug+0x18f/0x1a0
[ 2333.853399] ? handle_bug+0x63/0xa0
[ 2333.853407] ? exc_invalid_op+0x19/0x70
[ 2333.853414] ? asm_exc_invalid_op+0x1b/0x20
[ 2333.853422] ? __pfx_amdgpu_gfx_enforce_isolation_handler+0x10/0x10 [amdgpu]
[ 2333.853749] ? check_flush_dependency+0x124/0x130
[ 2333.853759] __flush_work+0xee/0x600
[ 2333.853766] ? srso_return_thunk+0x5/0x5f
[ 2333.853778] ? srso_return_thunk+0x5/0x5f
[ 2333.853783] ? __mutex_lock+0xc08/0xe20
[ 2333.853792] ? srso_return_thunk+0x5/0x5f
[ 2333.853798] ? trace_hardirqs_on+0x1e/0xd0
[ 2333.853804] ? srso_return_thunk+0x5/0x5f
[ 2333.853815] cancel_delayed_work_sync+0x71/0x80
[ 2333.853823] amdgpu_gfx_kfd_sch_ctrl+0x14f/0x290 [amdgpu]
[ 2333.854090] amdgpu_gfx_enforce_isolation_ring_begin_use+0x1d4/0x3e0 [amdgpu]
[ 2333.854347] ? cancel_delayed_work_sync+0x4f/0x80
[ 2333.854356] gfx_v12_0_ring_begin_use+0x1b/0x30 [amdgpu]
[ 2333.854618] amdgpu_ring_alloc+0x48/0x70 [amdgpu]
[ 2333.854854] amdgpu_ib_schedule+0x16f/0x8a0 [amdgpu]
[ 2333.855098] ? srso_return_thunk+0x5/0x5f
[ 2333.855105] amdgpu_job_run+0xad/0x260 [amdgpu]
[ 2333.855405] drm_sched_run_job_work+0x258/0x440 [gpu_sched]
[ 2333.855415] process_one_work+0x21e/0x680
[ 2333.855427] worker_thread+0x190/0x330
[ 2333.855434] ? __pfx_worker_thread+0x10/0x10
[ 2333.855439] kthread+0xe7/0x120
[ 2333.855444] ? __pfx_kthread+0x10/0x10
[ 2333.855450] ret_from_fork+0x3c/0x60
[ 2333.855455] ? __pfx_kthread+0x10/0x10
[ 2333.855460] ret_from_fork_asm+0x1a/0x30
[ 2333.855474] </TASK>
[ 2333.855477] irq event stamp: 103430
[ 2333.855480] hardirqs last enabled at (103429): [<ffffffff8da9237a>] irqentry_exit+0x3a/0x90
[ 2333.855486] hardirqs last disabled at (103430): [<ffffffff8da99e54>] __schedule+0xf84/0x1b00
[ 2333.855490] softirqs last enabled at (85926): [<ffffffff8c8fdabd>] __irq_exit_rcu+0x7d/0xa0
[ 2333.855495] softirqs last disabled at (85919): [<ffffffff8c8fdabd>] __irq_exit_rcu+0x7d/0xa0
Fixes: afefd6f24502 ("drm/amdgpu: Implement Enforce Isolation Handler for KGD/KFD serialization")
Cc: Christian König <christian.koenig@xxxxxxx>
Cc: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu.h | 2 ++
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 17 +++++++++++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 10 ++++++----
3 files changed, 25 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 87062c1adcdf..cbd31c164f9f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -123,6 +123,8 @@
#define GFX_SLICE_PERIOD_MS 250
+extern struct workqueue_struct *amdgpu_enforce_isolation_wq;
+
struct amdgpu_gpu_instance {
struct amdgpu_device *adev;
int mgpu_fan_enabled;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 7ca2ebdd3c95..562304d703a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -105,6 +105,8 @@ MODULE_FIRMWARE("amdgpu/navi12_gpu_info.bin");
#define AMDGPU_VBIOS_SKIP (1U << 0)
#define AMDGPU_VBIOS_OPTIONAL (1U << 1)
+struct workqueue_struct *amdgpu_enforce_isolation_wq;
+
static const struct drm_driver amdgpu_kms_driver;
const char *amdgpu_asic_name[] = {
@@ -4323,6 +4325,14 @@ int amdgpu_device_init(struct amdgpu_device *adev,
adev->gfx.enforce_isolation[i].xcp_id = i;
}
+ /* Allocate the enforce isolation workqueue with WQ_MEM_RECLAIM */
+ amdgpu_enforce_isolation_wq = alloc_workqueue("amdgpu_enforce_isolation_wq",
+ WQ_MEM_RECLAIM, 0);
+ if (!amdgpu_enforce_isolation_wq) {
+ dev_err(adev->dev, "Failed to allocate enforcement isolation workqueue\n");
+ return -ENOMEM;
+ }
+
INIT_WORK(&adev->xgmi_reset_work, amdgpu_device_xgmi_reset_func);
adev->gfx.gfx_off_req_count = 1;
@@ -4821,6 +4831,13 @@ void amdgpu_device_fini_sw(struct amdgpu_device *adev)
if (adev->mman.discovery_bin)
amdgpu_discovery_fini(adev);
+ /* Clean up the enforcement isolation workqueue */
+ if (amdgpu_enforce_isolation_wq) {
+ flush_workqueue(amdgpu_enforce_isolation_wq);
+ destroy_workqueue(amdgpu_enforce_isolation_wq);
+ amdgpu_enforce_isolation_wq = NULL;
+ }
+
amdgpu_reset_put_reset_domain(adev->reset_domain);
adev->reset_domain = NULL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 984e6ff6e463..0dabffe395bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1938,8 +1938,9 @@ static void amdgpu_gfx_kfd_sch_ctrl(struct amdgpu_device *adev, u32 idx,
if (adev->gfx.kfd_sch_req_count[idx] == 0 &&
adev->gfx.kfd_sch_inactive[idx]) {
- schedule_delayed_work(&adev->gfx.enforce_isolation[idx].work,
- msecs_to_jiffies(adev->gfx.enforce_isolation_time[idx]));
+ queue_delayed_work(amdgpu_enforce_isolation_wq,
+ &adev->gfx.enforce_isolation[idx].work,
+ msecs_to_jiffies(adev->gfx.enforce_isolation_time[idx]));
}
} else {
if (adev->gfx.kfd_sch_req_count[idx] == 0) {
@@ -1995,8 +1996,9 @@ void amdgpu_gfx_enforce_isolation_handler(struct work_struct *work)
}
if (fences) {
/* we've already had our timeslice, so let's wrap this up */
- schedule_delayed_work(&adev->gfx.enforce_isolation[idx].work,
- msecs_to_jiffies(1));
+ queue_delayed_work(amdgpu_enforce_isolation_wq,
+ &adev->gfx.enforce_isolation[idx].work,
+ msecs_to_jiffies(1));
} else {
/* Tell KFD to resume the runqueue */
if (adev->kfd.init_complete) {
--
2.34.1
