[RFC PATCH 12/13] drm/amdgpu/nbio: improve the way to manage irq reference count

[Jiang Liu]

Refactor nbio related code to improve the way to manage irq reference
count. Originally amdgpu_irq_get() is called from ip_blocks[].late_init
and amdgpu_irq_put is called from ip_blocks[].hw_fini. The asymmetric
design may cause issue under certain conditions. So
1) introduce amdgpu_nbio_ras_early_fini() to undo work done by
   amdgpu_nbio_ras_late_init().
2) remove call of amdgpu_irq_put in xxxx_hw_fini().
3) record the status where reference count is held for specific irq.

Signed-off-by: Jiang Liu <gerry at linux.alibaba.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c | 16 +++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h |  1 +
 drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c   |  1 +
 drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c   |  1 +
 drivers/gpu/drm/amd/amdgpu/soc15.c       | 16 ----------------
 5 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
index c75ce91f94ab..b8a69ceec2e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.c
@@ -64,13 +64,27 @@ int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *
 		r = amdgpu_irq_get(adev, &adev->nbio.ras_controller_irq, 0);
 		if (r)
 			goto late_fini;
+		amdgpu_ras_set_marker(adev, ras_block, AMDGPU_MARKER_IRQ0);
 		r = amdgpu_irq_get(adev, &adev->nbio.ras_err_event_athub_irq, 0);
 		if (r)
 			goto late_fini;
+		amdgpu_ras_set_marker(adev, ras_block, AMDGPU_MARKER_IRQ1);
 	}
 
 	return 0;
 late_fini:
-	amdgpu_ras_block_early_fini(adev, ras_block);
+	amdgpu_nbio_ras_early_fini(adev, ras_block);
 	return r;
 }
+
+void amdgpu_nbio_ras_early_fini(struct amdgpu_device *adev, struct ras_common_if *ras_block)
+{
+	if (amdgpu_ras_is_supported(adev, adev->nbio.ras_if->block)) {
+		if (amdgpu_ras_test_and_clear_marker(adev, ras_block, AMDGPU_MARKER_IRQ0))
+			amdgpu_irq_put(adev, &adev->nbio.ras_controller_irq, 0);
+		if (amdgpu_ras_test_and_clear_marker(adev, ras_block, AMDGPU_MARKER_IRQ1))
+			amdgpu_irq_put(adev, &adev->nbio.ras_err_event_athub_irq, 0);
+	}
+
+	amdgpu_ras_block_early_fini(adev, ras_block);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
index 79c2f807b9fe..e1edf75602c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_nbio.h
@@ -117,6 +117,7 @@ struct amdgpu_nbio {
 
 int amdgpu_nbio_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_nbio_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *ras_block);
+void amdgpu_nbio_ras_early_fini(struct amdgpu_device *adev, struct ras_common_if *ras_block);
 u64 amdgpu_nbio_get_pcie_replay_count(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
index 97782a73f4b0..6c727b77bb3c 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
@@ -665,6 +665,7 @@ struct amdgpu_nbio_ras nbio_v7_4_ras = {
 		},
 		.hw_ops = &nbio_v7_4_ras_hw_ops,
 		.ras_late_init = amdgpu_nbio_ras_late_init,
+		.ras_early_fini = amdgpu_nbio_ras_early_fini,
 	},
 	.handle_ras_controller_intr_no_bifring = nbio_v7_4_handle_ras_controller_intr_no_bifring,
 	.handle_ras_err_event_athub_intr_no_bifring = nbio_v7_4_handle_ras_err_event_athub_intr_no_bifring,
diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
index 8a0a63ac88d2..684a38a16247 100644
--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
+++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_9.c
@@ -703,6 +703,7 @@ struct amdgpu_nbio_ras nbio_v7_9_ras = {
 		},
 		.hw_ops = &nbio_v7_9_ras_hw_ops,
 		.ras_late_init = amdgpu_nbio_ras_late_init,
+		.ras_early_fini = amdgpu_nbio_ras_early_fini,
 	},
 	.handle_ras_controller_intr_no_bifring = nbio_v7_9_handle_ras_controller_intr_no_bifring,
 	.handle_ras_err_event_athub_intr_no_bifring = nbio_v7_9_handle_ras_err_event_athub_intr_no_bifring,
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 6fcdeb265a22..1dca7d7c813c 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1299,22 +1299,6 @@ static int soc15_common_hw_fini(struct amdgpu_ip_block *ip_block)
 	if (amdgpu_sriov_vf(adev))
 		xgpu_ai_mailbox_put_irq(adev);
 
-	/*
-	 * For minimal init, late_init is not called, hence RAS irqs are not
-	 * enabled.
-	 */
-	if ((!amdgpu_sriov_vf(adev)) &&
-	    (adev->init_lvl->level != AMDGPU_INIT_LEVEL_MINIMAL_XGMI) &&
-	    adev->nbio.ras_if &&
-	    amdgpu_ras_is_supported(adev, adev->nbio.ras_if->block)) {
-		if (adev->nbio.ras &&
-		    adev->nbio.ras->init_ras_controller_interrupt)
-			amdgpu_irq_put(adev, &adev->nbio.ras_controller_irq, 0);
-		if (adev->nbio.ras &&
-		    adev->nbio.ras->init_ras_err_event_athub_interrupt)
-			amdgpu_irq_put(adev, &adev->nbio.ras_err_event_athub_irq, 0);
-	}
-
 	return 0;
 }
 
-- 
2.43.5