[PATCH AUTOSEL 6.12 10/30] drm/amdgpu: Increase KIQ invalidate_tlbs timeout

[Sasha Levin]

From: Jay Cornwall <jay.cornwall@xxxxxxx>

[ Upstream commit 3666ed821832f42baaf25f362680dda603cde732 ]

KIQ invalidate_tlbs request has been seen to marginally exceed the
configured 100 ms timeout on systems under load.

All other KIQ requests in the driver use a 10 second timeout. Use a
similar timeout implementation on the invalidate_tlbs path.

v2: Poll once before msleep
v3: Fix return value

Signed-off-by: Jay Cornwall <jay.cornwall@xxxxxxx>
Cc: Kent Russell <kent.russell@xxxxxxx>
Reviewed-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c | 19 ++++++++++++++-----
 2 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 9b1e0ede05a45..b7aad43d9ad07 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -350,7 +350,6 @@ enum amdgpu_kiq_irq {
 	AMDGPU_CP_KIQ_IRQ_DRIVER0 = 0,
 	AMDGPU_CP_KIQ_IRQ_LAST
 };
-#define SRIOV_USEC_TIMEOUT  1200000 /* wait 12 * 100ms for SRIOV */
 #define MAX_KIQ_REG_WAIT       5000 /* in usecs, 5ms */
 #define MAX_KIQ_REG_BAILOUT_INTERVAL   5 /* in msecs, 5ms */
 #define MAX_KIQ_REG_TRY 1000
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 17a19d49d30a5..9d130d3af0b39 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -678,12 +678,10 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 				   uint32_t flush_type, bool all_hub,
 				   uint32_t inst)
 {
-	u32 usec_timeout = amdgpu_sriov_vf(adev) ? SRIOV_USEC_TIMEOUT :
-		adev->usec_timeout;
 	struct amdgpu_ring *ring = &adev->gfx.kiq[inst].ring;
 	struct amdgpu_kiq *kiq = &adev->gfx.kiq[inst];
 	unsigned int ndw;
-	int r;
+	int r, cnt = 0;
 	uint32_t seq;
 
 	/*
@@ -740,10 +738,21 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 
 		amdgpu_ring_commit(ring);
 		spin_unlock(&adev->gfx.kiq[inst].ring_lock);
-		if (amdgpu_fence_wait_polling(ring, seq, usec_timeout) < 1) {
+
+		r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+
+		might_sleep();
+		while (r < 1 && cnt++ < MAX_KIQ_REG_TRY &&
+		       !amdgpu_reset_pending(adev->reset_domain)) {
+			msleep(MAX_KIQ_REG_BAILOUT_INTERVAL);
+			r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+		}
+
+		if (cnt > MAX_KIQ_REG_TRY) {
 			dev_err(adev->dev, "timeout waiting for kiq fence\n");
 			r = -ETIME;
-		}
+		} else
+			r = 0;
 	}
 
 error_unlock_reset:
-- 
2.39.5