From: Jesse.Zhang <Jesse.Zhang@amd.com>
Date: Thu, 4 Sep 2025 01:50:00 +0000 (+0800)
Subject: drm/amdgpu/mes12: implement detect and reset callback
X-Git-Tag: v6.18-rc1~134^2~13^2~39
X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=724471254ee09949bd99358494e8f38d016616c1;p=thirdparty%2Flinux.git

drm/amdgpu/mes12: implement detect and reset callback

Implement support for the hung queue detect and reset
functionality.

v2: Always use AMDGPU_MES_SCHED_PIPE

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

diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 0075bb2ed66c8..998893dff08e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -47,6 +47,8 @@ static int mes_v12_0_kiq_hw_fini(struct amdgpu_device *adev);
 
 #define MES_EOP_SIZE   2048
 
+#define MES12_HUNG_DB_OFFSET_ARRAY_SIZE 4
+
 static void mes_v12_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
@@ -908,6 +910,32 @@ static int mes_v12_0_reset_hw_queue(struct amdgpu_mes *mes,
 			offsetof(union MESAPI__RESET, api_status));
 }
 
+static int mes_v12_0_detect_and_reset_hung_queues(struct amdgpu_mes *mes,
+						  struct mes_detect_and_reset_queue_input *input)
+{
+	union MESAPI__RESET mes_reset_queue_pkt;
+
+	memset(&mes_reset_queue_pkt, 0, sizeof(mes_reset_queue_pkt));
+
+	mes_reset_queue_pkt.header.type = MES_API_TYPE_SCHEDULER;
+	mes_reset_queue_pkt.header.opcode = MES_SCH_API_RESET;
+	mes_reset_queue_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+
+	mes_reset_queue_pkt.queue_type =
+		convert_to_mes_queue_type(input->queue_type);
+	mes_reset_queue_pkt.doorbell_offset_addr =
+		mes->hung_queue_db_array_gpu_addr;
+
+	if (input->detect_only)
+		mes_reset_queue_pkt.hang_detect_only = 1;
+	else
+		mes_reset_queue_pkt.hang_detect_then_reset = 1;
+
+	return mes_v12_0_submit_pkt_and_poll_completion(mes, AMDGPU_MES_SCHED_PIPE,
+			&mes_reset_queue_pkt, sizeof(mes_reset_queue_pkt),
+			offsetof(union MESAPI__RESET, api_status));
+}
+
 static int mes_v12_inv_tlb_convert_hub_id(uint8_t id)
 {
 	/*
@@ -960,6 +988,7 @@ static const struct amdgpu_mes_funcs mes_v12_0_funcs = {
 	.misc_op = mes_v12_0_misc_op,
 	.reset_hw_queue = mes_v12_0_reset_hw_queue,
 	.invalidate_tlbs_pasid = mes_v12_0_inv_tlbs_pasid,
+	.detect_and_reset_hung_queues = mes_v12_0_detect_and_reset_hung_queues,
 };
 
 static int mes_v12_0_allocate_ucode_buffer(struct amdgpu_device *adev,
@@ -1865,6 +1894,8 @@ static int mes_v12_0_early_init(struct amdgpu_ip_block *ip_block)
 	struct amdgpu_device *adev = ip_block->adev;
 	int pipe, r;
 
+	adev->mes.hung_queue_db_array_size =
+		MES12_HUNG_DB_OFFSET_ARRAY_SIZE;
 	for (pipe = 0; pipe < AMDGPU_MAX_MES_PIPES; pipe++) {
 		r = amdgpu_mes_init_microcode(adev, pipe);
 		if (r)