drm/amdgpu/sdma: Introduce is_guilty callbacks for sdma GFX and PAGE rings

This patch introduces the `is_guilty` callbacks for the GFX and PAGE rings.
These callbacks check if a ring is guilty of causing a timeout or error.

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 30 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index 1529c5516c13..4ef828df8e56 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -1606,6 +1606,34 @@ static int sdma_v4_4_2_soft_reset(struct amdgpu_ip_block *ip_block)
 	return 0;
 }
 
+static bool sdma_v4_4_2_is_queue_selected(struct amdgpu_device *adev, uint32_t instance_id, bool is_page_queue)
+{
+	uint32_t reg_offset = is_page_queue ? regSDMA_PAGE_CONTEXT_STATUS : regSDMA_GFX_CONTEXT_STATUS;
+	uint32_t context_status = RREG32(sdma_v4_4_2_get_reg_offset(adev, instance_id, reg_offset));
+
+	/* Check if the SELECTED bit is set */
+	return (context_status & SDMA_GFX_CONTEXT_STATUS__SELECTED_MASK) != 0;
+}
+
+static bool sdma_v4_4_2_ring_is_guilty(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t instance_id = ring->me;
+
+	return sdma_v4_4_2_is_queue_selected(adev, instance_id, false);
+}
+
+static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t instance_id = ring->me;
+
+	if (!adev->sdma.has_page_queue)
+		return false;
+
+	return sdma_v4_4_2_is_queue_selected(adev, instance_id, true);
+}
+
 static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -2055,6 +2083,7 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_ring_funcs = {
 	.emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 	.reset = sdma_v4_4_2_reset_queue,
+	.is_guilty = sdma_v4_4_2_ring_is_guilty,
 };
 
 static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = {
@@ -2086,6 +2115,7 @@ static const struct amdgpu_ring_funcs sdma_v4_4_2_page_ring_funcs = {
 	.emit_wreg = sdma_v4_4_2_ring_emit_wreg,
 	.emit_reg_wait = sdma_v4_4_2_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
+	.is_guilty = sdma_v4_4_2_page_ring_is_guilty,
 };
 
 static void sdma_v4_4_2_set_ring_funcs(struct amdgpu_device *adev)