If error happens before amdgpu_fence_driver_hw_init() gets called during
device probe, it will trigger a false warning in amdgpu_irq_put() as
below:
[ 1209.300996] ------------[ cut here ]------------
[ 1209.301061] WARNING: CPU: 48 PID: 293 at /tmp/amd.Rc9jFrl7/amd/amdgpu/amdgpu_irq.c:633 amdgpu_irq_put+0x45/0x70 [amdgpu]
[ 1209.301062] Modules linked in: ...
[ 1209.301093] CPU: 48 PID: 293 Comm: kworker/48:1 Kdump: loaded Tainted: G W OE 5.10.134-17.2.al8.x86_64 #1
[ 1209.301094] Hardware name: Alibaba Alibaba Cloud ECS/Alibaba Cloud ECS, BIOS 3.0.ES.AL.P.087.05 04/07/2024
[ 1209.301095] Workqueue: events work_for_cpu_fn
[ 1209.301159] RIP: 0010:amdgpu_irq_put+0x45/0x70 [amdgpu]
[ 1209.301160] Code: 48 8b 4e 10 48 83 39 00 74 2c 89 d1 48 8d 04 88 8b 08 85 c9 74 14 f0 ff 08 b8 00 00 00 00 74 05 c3 cc cc cc cc e9 8b fd ff ff <0f> 0b b8 ea ff ff ff c3 cc cc cc cc b8 ea ff ff ff c3 cc cc cc cc
[ 1209.301162] RSP: 0018:ffffb08a99c8fd88 EFLAGS: 00010246
[ 1209.301162] RAX: ffff9efe1bcbf500 RBX: ffff9efe1cc3e400 RCX: 0000000000000000
[ 1209.301163] RDX: 0000000000000000 RSI: ffff9efe1cc3b108 RDI: ffff9efe1cc00000
[ 1209.301163] RBP: ffff9efe1cc10818 R08: 0000000000000001 R09: 000000000000000d
[ 1209.301164] R10: ffffb08a99c8fb48 R11: ffffffffa2068018 R12: ffff9efe1cc109d0
[ 1209.301164] R13: ffff9efe1cc00010 R14: ffff9efe1cc00000 R15: ffff9efe1cc3b108
[ 1209.301165] FS: 0000000000000000(0000) GS:ffff9ff9fce00000(0000) knlGS:0000000000000000
[ 1209.301165] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 1209.301165] CR2: 00007fd0f6e860d0 CR3: 0000010092baa003 CR4: 0000000002770ee0
[ 1209.301166] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 1209.301166] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
[ 1209.301167] PKRU: 55555554
[ 1209.301167] Call Trace:
[ 1209.301225] amdgpu_fence_driver_hw_fini+0xda/0x110 [amdgpu]
[ 1209.301284] amdgpu_device_fini_hw+0xaf/0x200 [amdgpu]
[ 1209.301342] amdgpu_driver_load_kms+0x7f/0xc0 [amdgpu]
[ 1209.301400] amdgpu_pci_probe+0x1cd/0x4a0 [amdgpu]
[ 1209.301401] local_pci_probe+0x40/0xa0
[ 1209.301402] work_for_cpu_fn+0x13/0x20
[ 1209.301403] process_one_work+0x1ad/0x380
[ 1209.301404] worker_thread+0x1c8/0x310
[ 1209.301405] ? process_one_work+0x380/0x380
[ 1209.301406] kthread+0x118/0x140
[ 1209.301407] ? __kthread_bind_mask+0x60/0x60
[ 1209.301408] ret_from_fork+0x1f/0x30
[ 1209.301410] ---[ end trace 733f120fe2ab13e5 ]---
[ 1209.301418] ------------[ cut here ]------------
Signed-off-by: Jiang Liu <gerry@xxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 9 +++++++--
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 1 +
2 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index b5e87b515139..0e41a535e05f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -614,9 +614,11 @@ void amdgpu_fence_driver_hw_fini(struct amdgpu_device *adev)
if (!drm_dev_is_unplugged(adev_to_drm(adev)) &&
ring->fence_drv.irq_src &&
- amdgpu_fence_need_ring_interrupt_restore(ring))
+ ring->fence_drv.irq_enabled) {
amdgpu_irq_put(adev, ring->fence_drv.irq_src,
ring->fence_drv.irq_type);
+ ring->fence_drv.irq_enabled = false;
+ }
del_timer_sync(&ring->fence_drv.fallback_timer);
}
@@ -693,9 +695,12 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
/* enable the interrupt */
if (ring->fence_drv.irq_src &&
- amdgpu_fence_need_ring_interrupt_restore(ring))
+ !ring->fence_drv.irq_enabled &&
+ amdgpu_fence_need_ring_interrupt_restore(ring)) {
amdgpu_irq_get(adev, ring->fence_drv.irq_src,
ring->fence_drv.irq_type);
+ ring->fence_drv.irq_enabled = true;
+ }
}
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index dee5a1b4e572..959d474a0516 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -118,6 +118,7 @@ struct amdgpu_fence_driver {
uint32_t sync_seq;
atomic_t last_seq;
bool initialized;
+ bool irq_enabled;
struct amdgpu_irq_src *irq_src;
unsigned irq_type;
struct timer_list fallback_timer;
--
2.43.5
