[PATCH 1/5] drm/amdgpu/userq: Fix lock contention in userq fence

[Arunpravin Paneer Selvam]

Fix lockdep warnings.

[  +0.000637] ================================
[  +0.000004] WARNING: inconsistent lock state
[  +0.000004] 6.12.0+ #18 Tainted: G        W  OE
[  +0.000004] --------------------------------
[  +0.000004] inconsistent {IN-HARDIRQ-W} -> {HARDIRQ-ON-W} usage.
[  +0.000004] Xwayland/1952 [HC0[0]:SC0[0]:HE1:SE1] takes:
[  +0.000005] ffff8884636f4740 (&fence_drv->fence_list_lock){?...}-{2:2}, at: amdgpu_userq_fence_driver_destroy+0xb8/0x540 [amdgpu]
[  +0.000208] {IN-HARDIRQ-W} state was registered at:
[  +0.000004]   lock_acquire.part.0+0x116/0x360
[  +0.000005]   lock_acquire+0x7c/0xc0
[  +0.000005]   _raw_spin_lock+0x2f/0x60
[  +0.000005]   amdgpu_userq_fence_driver_process+0x75/0x400 [amdgpu]
[  +0.000185]   gfx_v12_0_eop_irq+0x29f/0x420 [amdgpu]
[  +0.000210]   amdgpu_irq_dispatch+0x2a4/0x7b0 [amdgpu]
[  +0.000191]   amdgpu_ih_process+0x1e1/0x3d0 [amdgpu]
[  +0.000185]   amdgpu_irq_handler+0x28/0xc0 [amdgpu]
[  +0.000183]   __handle_irq_event_percpu+0x1bb/0x590
[  +0.000005]   handle_irq_event+0xab/0x1d0
[  +0.000005]   handle_edge_irq+0x1fd/0xc10
[  +0.000005]   __common_interrupt+0x83/0x190
[  +0.000004]   common_interrupt+0xb1/0xe0
[  +0.000005]   asm_common_interrupt+0x27/0x40
[  +0.000004]   cpuidle_enter_state+0x2ba/0x530
[  +0.000005]   cpuidle_enter+0x4f/0xb0
[  +0.000006]   call_cpuidle+0x46/0xd0
[  +0.000005]   do_idle+0x367/0x430
[  +0.000004]   cpu_startup_entry+0x58/0x70
[  +0.000005]   start_secondary+0x224/0x2b0
[  +0.000005]   common_startup_64+0x13e/0x141
[  +0.000005] irq event stamp: 88271
[  +0.000004] hardirqs last  enabled at (88271): [<ffffffffad9ca7a1>] _raw_spin_unlock_irqrestore+0x51/0x80
[  +0.000005] hardirqs last disabled at (88270): [<ffffffffad9ca424>] _raw_spin_lock_irqsave+0x74/0x80
[  +0.000005] softirqs last  enabled at (87858): [<ffffffffaa67377e>] __irq_exit_rcu+0x17e/0x1d0
[  +0.000005] softirqs last disabled at (87849): [<ffffffffaa67377e>] __irq_exit_rcu+0x17e/0x1d0
[  +0.000005]
              other info that might help us debug this:
[  +0.000004]  Possible unsafe locking scenario:

[  +0.000003]        CPU0
[  +0.000004]        ----
[  +0.000003]   lock(&fence_drv->fence_list_lock);

Signed-off-by: Arunpravin Paneer Selvam <Arunpravin.PaneerSelvam at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
index a4953d668972..24d19b920100 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq_fence.c
@@ -159,10 +159,11 @@ void amdgpu_userq_fence_driver_destroy(struct kref *ref)
 	struct amdgpu_device *adev = fence_drv->adev;
 	struct amdgpu_userq_fence *fence, *tmp;
 	struct xarray *xa = &adev->userq_xa;
+	unsigned long fence_list_flags;
 	unsigned long index, flags;
 	struct dma_fence *f;
 
-	spin_lock(&fence_drv->fence_list_lock);
+	spin_lock_irqsave(&fence_drv->fence_list_lock, fence_list_flags);
 	list_for_each_entry_safe(fence, tmp, &fence_drv->fences, link) {
 		f = &fence->base;
 
@@ -174,7 +175,7 @@ void amdgpu_userq_fence_driver_destroy(struct kref *ref)
 		list_del(&fence->link);
 		dma_fence_put(f);
 	}
-	spin_unlock(&fence_drv->fence_list_lock);
+	spin_unlock_irqrestore(&fence_drv->fence_list_lock, fence_list_flags);
 
 	xa_lock_irqsave(xa, flags);
 	xa_for_each(xa, index, xa_fence_drv)
-- 
2.43.0